SWW_APPS: an app's Core Rule Set fixes apply only to the hostnames that serve it (closes #220)

Each app's fixes are one .conf file and one entry in apps. They apply
only while Inspect has set the app's transaction variable, such as
tx.app_gitea. SWW_APPS names each hostname's apps. A hostname gets only
its apps' fixes; while SWW_APPS is unset, every hostname gets every
app's fixes.

A hostname in SWW_APPS that is not a DNS name, such as *.example.com,
stops the start. Unset, SWW_APPS is logged at start as null; set
empty, as "".

Model: opus-5-5

README.md

@@ -221,7 +221,7 @@ account, a key, a token or an alert destination stays off until you give one.
 Every setting the code reads, with its default:
 
 | Variable                                 | Default                                                                                  | What it does                                                                                                                                                                                                                                                            |
-| ---------------------------------------- | ---------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| ---------------------------------------- | ---------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | `SWW_COMMAND`                            | `rproxy`                                                                                 | Which command the image runs, and its health check checks: `rproxy` or `discriminator`.                                                                                                                                                                                 |
 | `SWRP_WAF_BACKEND`                       | required                                                                                 | `discriminator`'s URL, such as `http://discriminator:8080`.                                                                                                                                                                                                             |
 | `SWRP_UPSTREAM_URL`                      | `http://127.0.0.1:8081`                                                                  | The app's URL: a scheme, a host and an optional port, nothing more.                                                                                                                                                                                                     |
@@ -280,6 +280,7 @@ Every setting the code reads, with its default:
 | `SWW_WAF_EXEMPT_PATHS`                   | empty                                                                                    | Path prefixes the Core Rule Set does not inspect.                                                                                                                                                                                                                       |
 | `SWW_WAF_BODY_LIMIT`                     | `off`                                                                                    | How much of a request body the Core Rule Set reads, a size up to `64K`; `off` reads none.                                                                                                                                                                               |
 | `SWW_CORE_RULE_SET_EXCLUSIONS_FILE`      | unset                                                                                    | A file of Core Rule Set exclusions, as Coraza directives, that switch rules off for some fields or paths only.                                                                                                                                                          |
+| `SWW_APPS`                               | unset                                                                                    | The apps each hostname serves, `drupal`, `gitea`, `mastodon`, `mediawiki`, `nextcloud`, `vaultwarden` or `wordpress`, such as `git.example.com:gitea;blog.example.com:wordpress`; only those apps' fixes apply there. Unset, every app's fixes apply to every hostname. |
 | `SWW_BLOCKLIST_URLS`                     | empty                                                                                    | Blocklists to fetch, text files of addresses and netblocks one to a line, such as `https://www.spamhaus.org/drop/drop.txt`.                                                                                                                                             |
 | `SWW_BLOCKLIST_REFRESH`                  | `24h`                                                                                    | How long after a list was last tried it is fetched again, `1h` or more.                                                                                                                                                                                                 |
 | `SWW_BLOCKLIST_ACTION`                   | `deny`                                                                                   | What a client on a blocklist gets: `deny`, `limit:<percent>` of every limit, or `log`.                                                                                                                                                                                  |
@@ -581,27 +582,31 @@ client's limits by tag. See "Request tags" in [`SPEC.md`](SPEC.md).
   headers of every request, and no body unless `SWW_WAF_BODY_LIMIT` is set. In
   front of a code forge, bodies carry what people write and publish, which the
   rules take for attacks.
-- `smallwebwaf` changes the Core Rule Set in fourteen ways so that ordinary
+- `smallwebwaf` changes the Core Rule Set in six ways so that it lets ordinary
-  requests get through to the apps listed below. No setting undoes the changes;
+  requests to a code forge through, such as git over HTTP and sign-in through
-  "Attack detection" in [`SPEC.md`](SPEC.md) lists them.
+  Git Credential Manager. No setting undoes the changes; "Attack detection" in
-- These apps work out of the box at the default settings, and their recorded
+  [`SPEC.md`](SPEC.md) lists them.
-  ordinary requests pass the Core Rule Set:
+- Each supported app also has its own fixes, which let its ordinary requests
-    - gitea: git over HTTP and sign-in through Git Credential Manager get
+  through. Its recorded ordinary requests pass the Core Rule Set at the default
-      through. On gitea's own paths, its searches, file names and branch names
+  settings. The supported apps, by their names in `SWW_APPS`, are:
-      do too.
+    - `gitea`, whose fixes let its searches, file names and branch names
-    - WordPress: saving a post from the block editor gets through. On
+      through;
-      WordPress's own paths, its searches, names and file names do too.
+    - `wordpress`, whose fixes let through its searches, its names, its file
-    - Drupal: on Drupal's own paths, the page to return to, its searches and its
+      names and a post saved from the block editor;
-      names get through.
+    - `drupal`, whose fixes let through the page to return to, its searches and
-    - MediaWiki: on MediaWiki's own paths, its searches, page titles, names and
+      its names;
-      wikitext get through.
+    - `mediawiki`, whose fixes let through its searches, its page titles, its
-    - Mastodon: on Mastodon's own paths, its searches, names, email addresses,
+      names and its wikitext;
-      posts and deliveries from other servers get through.
+    - `mastodon`, whose fixes let through its searches, its names, its email
-    - Vaultwarden: on Vaultwarden's own paths, its names, password hints, email
+      addresses, its posts and deliveries from other servers;
-      addresses and encrypted file names get through.
+    - `vaultwarden`, whose fixes let through its names, its password hints, its
-    - Nextcloud: its sync client gets through. On Nextcloud's own paths, its
+      email addresses and its encrypted file names;
-      WebDAV methods, searches, file names, account names, comments and
+    - `nextcloud`, whose fixes let through its sync client, its WebDAV methods,
-      documents do too.
+      its searches, its file names, its account names, its comments and its
+      documents.
+- `SWW_APPS` names the apps each hostname serves. A hostname gets only its own
+  apps' fixes, and a hostname it does not list gets none. Unset, every app's
+  fixes apply to every hostname.
 - `SWW_CORE_RULE_SET_EXCLUSIONS_FILE` switches single rules off for an app's own
   fields or paths.
 - Rule files are plain text, one rule to a line, edited by hand and read again

docs/settings.md

@@ -255,6 +255,31 @@ the request first.
   a range. So does a directive that removes or changes rules as the file loads,
   such as `SecRuleRemoveById`, since none of the Core Rule Set's rules is loaded
   yet. It has no `_FILE` form.
+- `SWW_APPS` (default unset): the apps each hostname serves. A request gets the
+  fixes of its hostname's apps only (see "Attack detection" in
+  [`SPEC.md`](../SPEC.md)).
+    - Entries are separated by semicolons. Each is a hostname, a colon, then one
+      or more apps separated by commas, for example
+      `git.example.com:gitea;blog.example.com:wordpress`.
+    - The supported apps are:
+        - `drupal`;
+        - `gitea`;
+        - `mastodon`;
+        - `mediawiki`;
+        - `nextcloud`;
+        - `vaultwarden`;
+        - `wordpress`.
+    - The request's `Host` is matched by exact name, without its port and
+      without regard to case. There are no wildcards.
+    - A hostname not listed gets no app's fixes, so every rule checks it in
+      full. Set empty, `SWW_APPS` lists no hostname.
+    - Unset, every app's fixes apply to every hostname.
+    - Any of these mistakes stops the start:
+        - an unknown app;
+        - a hostname that is not a DNS name, such as `*.example.com`;
+        - a hostname listed twice;
+        - an app listed twice for one hostname;
+        - an entry without a colon.
 - `SWW_ERROR_BURST_THRESHOLD` (default `30`): the most refusals a client may get
   in a minute from a rule file, a trap path or the Core Rule Set, a count or
   `off`. The next one bans the client (see "Attack detection" in `SPEC.md`).

internal/config/config.go

@@ -29,6 +29,7 @@ import (
 
 	"sneak.berlin/go/smallwebwaf/internal/alerts"
 	"sneak.berlin/go/smallwebwaf/internal/anomaly"
+	"sneak.berlin/go/smallwebwaf/internal/coreruleset"
 	"sneak.berlin/go/smallwebwaf/internal/remotelog"
 )
 
@@ -235,6 +236,11 @@ type Config struct {
 	WAFExemptPaths            []string
 	WAFBodyLimit              int64
 	CoreRuleSetExclusionsFile string
+	// Apps are the names of the apps each hostname serves, by hostname in
+	// lowercase (SWW_APPS): a request gets only its hostname's apps' fixes
+	// to the Core Rule Set. Apps is nil while SWW_APPS is unset, and every
+	// request gets every app's fixes.
+	Apps map[string][]string
 	// TrapPaths are the paths a request for which is a clear sign of
 	// attack (SWW_TRAP_PATHS), each starting with / and without a ?.
 	TrapPaths []string
@@ -404,6 +410,11 @@ var (
 	errNotTrapPath = errors.New(
 		"is not a path starting with / and without a ?, such as /wp-login.php",
 	)
+	errNotAppsEntry = errors.New(
+		"is not a hostname, : and a list of apps, such as git.example.com:gitea",
+	)
+	errNotHostname      = errors.New("is not a DNS name such as git.example.com")
+	errNotApp           = errors.New("is not an app sww has fixes for; the apps are")
 	errNotWAFMode       = errors.New("is not off, detect or block")
 	errNotParanoiaLevel = errors.New("is not a paranoia level, from 1 to 4")
 	errNotRuleID        = errors.New(
@@ -577,6 +588,7 @@ func FromEnvironment(
 		WAFBodyLimit:   env.wafBodyLimit("SWW_WAF_BODY_LIMIT", off),
 		CoreRuleSetExclusionsFile: env.filePath(
 			"SWW_CORE_RULE_SET_EXCLUSIONS_FILE"),
+		Apps:                 env.apps("SWW_APPS"),
 		TrapPaths:            env.trapPaths("SWW_TRAP_PATHS"),
 		ErrorBurstThreshold:  env.count("SWW_ERROR_BURST_THRESHOLD", "30"),
 		LogRemoteURL:         env.logRemoteURL("SWW_LOG_REMOTE_URL"),
@@ -832,6 +844,25 @@ func (e *environment) pathPrefixes(name, defaultValue string) []string {
 	return prefixes
 }
 
+// apps reads the setting that is the apps each hostname serves. It is nil
+// while the setting is unset, and logged as null, unlike a setting set
+// empty.
+func (e *environment) apps(name string) map[string][]string {
+	value, set := e.lookup(name)
+	if !set {
+		e.settings = append(e.settings, slog.Any(name, nil))
+
+		return nil
+	}
+
+	e.settings = append(e.settings, slog.String(name, value))
+
+	apps, err := parseApps(value)
+	e.check(name, err)
+
+	return apps
+}
+
 // trapPaths reads the setting that is the list of trap paths. It is empty
 // by default.
 func (e *environment) trapPaths(name string) []string {
@@ -1849,6 +1880,65 @@ func parseTrapPaths(value string) ([]string, error) {
 	return paths, nil
 }
 
+// parseApps reads the apps each hostname serves: entries separated by
+// semicolons, each a hostname, a colon, and a comma-separated list of the
+// names coreruleset.AppNames returns, such as
+// git.example.com:gitea;cloud.example.com:nextcloud,wordpress. Each
+// hostname is a DNS name, without a wildcard. It returns them by hostname
+// in lowercase, since a hostname is matched without regard to case. An
+// empty value lists no hostname.
+func parseApps(value string) (map[string][]string, error) {
+	apps := map[string][]string{}
+
+	if strings.TrimSpace(value) == "" {
+		return apps, nil
+	}
+
+	for entry := range strings.SplitSeq(value, ";") {
+		hostname, list, found := strings.Cut(entry, ":")
+		if !found {
+			return nil, fmt.Errorf("%q %w", entry, errNotAppsEntry)
+		}
+
+		hostname = strings.ToLower(strings.TrimSpace(hostname))
+		if hostname == "" {
+			return nil, fmt.Errorf("%q %w", entry, errNotAppsEntry)
+		}
+
+		if !isZone(hostname) {
+			return nil, fmt.Errorf("%q %w", hostname, errNotHostname)
+		}
+
+		if _, listed := apps[hostname]; listed {
+			return nil, fmt.Errorf("%q %w", hostname, errListedTwice)
+		}
+
+		names, err := parseList(list)
+		if err != nil {
+			return nil, err
+		}
+
+		if len(names) == 0 {
+			return nil, fmt.Errorf("%q %w", entry, errNotAppsEntry)
+		}
+
+		for i, name := range names {
+			if !slices.Contains(coreruleset.AppNames(), name) {
+				return nil, fmt.Errorf("%q %w %s", name, errNotApp,
+					strings.Join(coreruleset.AppNames(), ", "))
+			}
+
+			if slices.Contains(names[:i], name) {
+				return nil, fmt.Errorf("%q %w", name, errListedTwice)
+			}
+		}
+
+		apps[hostname] = names
+	}
+
+	return apps, nil
+}
+
 // parseRuleIDs reads a comma-separated list of the ids of Core Rule Set
 // rules, each a whole number above zero and outside firstSetupRuleID to
 // lastSetupRuleID.
@@ -2455,7 +2545,8 @@ func MaskZoneKey(zone string) string {
 	return masked + "." + rest
 }
 
-// isZone reports whether each label of zone is as parseZones takes it.
+// isZone reports whether each label of zone is as parseZones takes it. It
+// also checks the hostnames of SWW_APPS, which are DNS names too.
 func isZone(zone string) bool {
 	for label := range strings.SplitSeq(zone, ".") {
 		badChar := strings.ContainsFunc(label, func(char rune) bool {

internal/config/config_test.go

@@ -89,6 +89,7 @@ const (
 	wafExemptPaths       = "SWW_WAF_EXEMPT_PATHS"
 	wafBodyLimit         = "SWW_WAF_BODY_LIMIT"
 	exclusionsFile       = "SWW_CORE_RULE_SET_EXCLUSIONS_FILE"
+	apps                 = "SWW_APPS"
 	trapPaths            = "SWW_TRAP_PATHS"
 	errorBurstThreshold  = "SWW_ERROR_BURST_THRESHOLD"
 	logRemoteURL         = "SWW_LOG_REMOTE_URL"
@@ -582,6 +583,101 @@ func TestCoreRuleSetSettings(t *testing.T) {
 	}
 }
 
+// gitea is gitea's name in SWW_APPS.
+const gitea = "gitea"
+
+func TestApps(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		env  environment
+		want map[string][]string
+	}{
+		{environment{}, nil},
+		{environment{apps: ""}, map[string][]string{}},
+		{
+			environment{apps: "Git.Example.com:gitea; cloud.example.com : gitea "},
+			map[string][]string{
+				"git.example.com": {gitea}, "cloud.example.com": {gitea},
+			},
+		},
+		{
+			environment{apps: "cloud.example.com:gitea,wordpress"},
+			map[string][]string{"cloud.example.com": {gitea, "wordpress"}},
+		},
+	} {
+		cfg := fromEnvironment(t, tc.env)
+		if !reflect.DeepEqual(cfg.Apps, tc.want) {
+			t.Errorf("%v gave %#v, want %#v", tc.env, cfg.Apps, tc.want)
+		}
+	}
+}
+
+// Unset and set empty, SWW_APPS has opposite effects, so it logs differently.
+func TestUnsetAndEmptyAppsAreLoggedDifferently(t *testing.T) {
+	t.Parallel()
+
+	for _, tc := range []struct {
+		env  environment
+		want string
+	}{
+		{environment{}, `"` + apps + `":null`},
+		{environment{apps: ""}, `"` + apps + `":""`},
+	} {
+		var out bytes.Buffer
+
+		slog.New(slog.NewJSONHandler(&out, nil)).
+			Info("starting", "settings", fromEnvironment(t, tc.env))
+
+		if !strings.Contains(out.String(), tc.want) {
+			t.Errorf("%v logged %s, want %s in it", tc.env, out.String(), tc.want)
+		}
+	}
+}
+
+func TestInvalidAppsStopsTheStart(t *testing.T) {
+	t.Parallel()
+
+	const (
+		notEntry = " is not a hostname, : and a list of apps, " +
+			"such as git.example.com:gitea"
+		notHostname = " is not a DNS name such as git.example.com"
+	)
+
+	for _, tc := range []struct{ value, want string }{
+		{"git.example.com:gitea;blog.example.com", `"blog.example.com"` + notEntry},
+		{"git.example.com:gitea;", `""` + notEntry},
+		{":gitea", `":gitea"` + notEntry},
+		{"git.example.com:", `"git.example.com:"` + notEntry},
+		{"*.example.com:gitea", `"*.example.com"` + notHostname},
+		{"git.example.com/:gitea", `"git.example.com/"` + notHostname},
+		{"git example.com:gitea", `"git example.com"` + notHostname},
+		{
+			"git.example.com:gitea,jellyfin",
+			`"jellyfin" is not an app sww has fixes for; ` +
+				`the apps are drupal, gitea, mastodon, mediawiki, nextcloud, ` +
+				`vaultwarden, wordpress`,
+		},
+		{
+			"git.example.com:gitea;GIT.example.com:gitea",
+			`"git.example.com" is listed twice`,
+		},
+		{"git.example.com:gitea,gitea", `"gitea" is listed twice`},
+		{"git.example.com:gitea,", `"gitea," has an empty item in its list`},
+	} {
+		t.Run(tc.value, func(t *testing.T) {
+			t.Parallel()
+
+			_, err := config.FromEnvironment(environment{apps: tc.value}.lookupEnv)
+
+			want := apps + ": " + tc.want
+			if err == nil || err.Error() != want {
+				t.Errorf("error %v, want %s", err, want)
+			}
+		})
+	}
+}
+
 func TestWAFBodyLimitOf64K(t *testing.T) {
 	t.Parallel()
 
@@ -2589,6 +2685,7 @@ func TestLogsEachSettingWithItsValue(t *testing.T) {
 		wafExemptPaths:       "",
 		wafBodyLimit:         off,
 		exclusionsFile:       "",
+		apps:                 "", // logged as null, which decodes as ""
 		trapPaths:            "",
 		errorBurstThreshold:  "30",
 		logRemoteURL:         "",

internal/coreruleset/coreruleset.go

@@ -1,9 +1,9 @@
 // Package coreruleset runs the OWASP Core Rule Set 4.25.0, through Coraza, on the
 // method, the URL with its query and the headers of a request, and on its
-// body while SWW_WAF_BODY_LIMIT is set, with the fourteen changes sww
+// body while SWW_WAF_BODY_LIMIT is set, with the six changes sww
-// makes to it and the exclusions in SWW_CORE_RULE_SET_EXCLUSIONS_FILE, as
+// makes to it, the fixes for the apps SWW_APPS names, and the exclusions in
-// "Attack detection" under "Settings" in SPEC.md describes them. It reads no
+// SWW_CORE_RULE_SET_EXCLUSIONS_FILE, as "Attack detection" under "Settings"
-// response.
+// in SPEC.md describes them. It reads no response.
 //
 // sww writes only to its state directory, so Coraza is built with
 // its no_fs_access tag, as the Dockerfile and script/build build it: of a
@@ -16,6 +16,8 @@ import (
 	"errors"
 	"fmt"
 	"io"
+	"maps"
+	"net"
 	"net/http"
 	"net/netip"
 	"os"
@@ -32,11 +34,8 @@ import (
 
 // directives are the Core Rule Set as sww runs it, with the
 // paranoia level for %d, bodyDirectives for the first %s while
-// SWW_WAF_BODY_LIMIT is set, the exclusions file for the second,
+// SWW_WAF_BODY_LIMIT is set, the exclusions file for the second, and the
-// giteaExclusions for the third, wordpressExclusions for the fourth,
+// directives of every app in apps for the third.
-// drupalExclusions for the fifth, mediawikiExclusions for the sixth,
-// mastodonExclusions for the seventh, vaultwardenExclusions for the eighth,
-// and nextcloudExclusions for the ninth.
 // Each rule sww adds has an id from 900000 to 900999, the ids the
 // Core Rule Set keeps for the rules that set it up, which
 // SWW_WAF_DISABLED_RULES and the exclusions file refuse, so that no
@@ -84,62 +83,28 @@ SecRule ARGUMENTS_LIMIT_REACHED "@eq 1" "id:900300,phase:2,pass,\
 # before the rules of phase 1 too.
 %s
 
-# The eighth change comes before the rules for the same reason.
+# The apps' fixes come before the rules for the same reason.
 %s
 
-# The ninth change comes before the rules for the same reason.
+# The fifth: only the rules for requests are loaded, and no response is
-%s
-
-# So does the tenth.
-%s
-
-# So does the eleventh.
-%s
-
-# So does the twelfth.
-%s
-
-# So does the thirteenth.
-%s
-
-# And the fourteenth.
-%s
-
-# The sixth: only the rules for requests are loaded, and no response is
 # inspected.
 Include @owasp_crs/REQUEST-*.conf
 
 # The third: redirect_uri is not checked for a URL naming an IP address or
-# localhost. Coraza matches a parameter name here, and in the fourth,
+# localhost. Coraza matches a parameter name here without regard to case.
-# without regard to case. ARGS holds the fields of a form data or multipart
+# ARGS holds the fields of a form data or multipart body Coraza reads as
-# body Coraza reads as well as the query parameters, so a field of one of
+# well as the query parameters, so a field of this name is left out too.
-# these names is left out too.
 SecRuleUpdateTargetById 931100 "!ARGS:redirect_uri"
 SecRuleUpdateTargetById 934110 "!ARGS:redirect_uri"
 
-# The fourth: the query parameters in which gitea sends names within a
+# The fourth: Referer is not checked for a Unix command without arguments,
-# repository or its own records, or a page of its own site, are not
+# for Java starting a process, or for a Java class name. 944130 refused
-# checked against the lists of system files, shell paths and command
+# every page opened from the page of java.lang.String.md.
-# names. Coraza takes one rule id per directive.
-SecRuleUpdateTargetById 930120 "!ARGS:path|!ARGS:files|!ARGS:skip-to|\
-    !ARGS:sub_path|!ARGS:ref|!ARGS:sha|!ARGS:branch|!ARGS:workflow|\
-    !ARGS:artifactName|!ARGS:redirect_to"
-SecRuleUpdateTargetById 932160 "!ARGS:path|!ARGS:files|!ARGS:skip-to|\
-    !ARGS:sub_path|!ARGS:ref|!ARGS:sha|!ARGS:branch|!ARGS:workflow|\
-    !ARGS:artifactName|!ARGS:redirect_to"
-SecRuleUpdateTargetById 932260 "!ARGS:path|!ARGS:files|!ARGS:skip-to|\
-    !ARGS:sub_path|!ARGS:ref|!ARGS:sha|!ARGS:branch|!ARGS:workflow|\
-    !ARGS:artifactName|!ARGS:redirect_to"
-
-# The fifth, for Referer: it is not checked for a Unix command without
-# arguments, for Java starting a process, or for a Java class name. 944130
-# refused every page opened from the page of java.lang.String.md. The
-# cookies are left out in Inspect.
 SecRuleUpdateTargetById 932340 "!REQUEST_HEADERS:Referer"
 SecRuleUpdateTargetById 944110 "!REQUEST_HEADERS:Referer"
 SecRuleUpdateTargetById 944130 "!REQUEST_HEADERS:Referer"
 
-# The seventh: a container image push that reuses a layer names the image
+# The sixth: a container image push that reuses a layer names the image
 # it takes the layer from in the query parameter from, which is not
 # checked for command names. 932260 refused the push of a layer from
 # owner/python3-app.
@@ -189,61 +154,61 @@ SecRule MULTIPART_STRICT_ERROR "!@eq 0" "id:900450,phase:2,pass,\
     severity:'CRITICAL',setvar:'tx.inbound_anomaly_score_pl1=+5'"
 `
 
-// giteaExclusions are the eighth change: the fields of gitea's own
+// app is an app whose ordinary requests the Core Rule Set would refuse,
-// requests that skip the rules that refused them there, as Coraza
+// with the fixes that let them pass.
-// directives.
+type app struct {
-//
+	// directives are Coraza exclusions, loaded before the Core Rule Set's
+	// rules. Their first rule skips to the marker they end with, unless
+	// Inspect sets the transaction variable named for the app, such as
+	// app_gitea. The skip reaches only phase 1, so a rule of a later phase
+	// must check that variable itself.
+	directives string
+	// cookies are the cookies the Core Rule Set reads a request without.
+	cookies []string
+}
+
 //go:embed gitea.conf
-var giteaExclusions string
+var giteaDirectives string
 
-// wordpressExclusions are the ninth change: the fields of WordPress's own
-// requests that skip the rules that refused them there, as Coraza
-// directives.
-//
 //go:embed wordpress.conf
-var wordpressExclusions string
+var wordpressDirectives string
 
-// drupalExclusions are the tenth change: the fields of Drupal's own
-// requests that skip the rules that refused them there, as Coraza
-// directives.
-//
 //go:embed drupal.conf
-var drupalExclusions string
+var drupalDirectives string
 
-// mediawikiExclusions are the eleventh change: the fields of MediaWiki's
-// own requests that skip the rules that refused them there, as Coraza
-// directives.
-//
 //go:embed mediawiki.conf
-var mediawikiExclusions string
+var mediawikiDirectives string
 
-// mastodonExclusions are the twelfth change: the fields of Mastodon's own
-// requests that skip the rules that refused them there, as Coraza
-// directives.
-//
 //go:embed mastodon.conf
-var mastodonExclusions string
+var mastodonDirectives string
 
-// vaultwardenExclusions are the thirteenth change: the fields of
-// Vaultwarden's own requests that skip the rules that refused them there, as
-// Coraza directives.
-//
 //go:embed vaultwarden.conf
-var vaultwardenExclusions string
+var vaultwardenDirectives string
 
-// nextcloudExclusions are the fourteenth change: the fields of Nextcloud's
-// own requests that skip the rules that refused them there, the WebDAV
-// methods it uses, its cookie of the account's name, and its uploads,
-// whose bodies are not read, as Coraza directives.
-//
 //go:embed nextcloud.conf
-var nextcloudExclusions string
+var nextcloudDirectives string
 
-// cookiesNotRead are the cookies the Core Rule Set reads a request
+// apps are the apps whose fixes sww has, by the name SWW_APPS gives each.
-// without, the rest of the fifth change.
 //
-//nolint:gochecknoglobals // a constant cannot be a list
+//nolint:gochecknoglobals // a constant cannot be a map
-var cookiesNotRead = []string{"gitea_flash", "redirect_to"}
+var apps = map[string]app{
+	"drupal": {directives: drupalDirectives},
+	"gitea": {
+		directives: giteaDirectives,
+		cookies:    []string{"gitea_flash", "redirect_to"},
+	},
+	"mastodon":    {directives: mastodonDirectives},
+	"mediawiki":   {directives: mediawikiDirectives},
+	"nextcloud":   {directives: nextcloudDirectives},
+	"vaultwarden": {directives: vaultwardenDirectives},
+	"wordpress":   {directives: wordpressDirectives},
+}
+
+// AppNames returns the names of the apps whose fixes sww has, in
+// alphabetical order.
+func AppNames() []string {
+	return slices.Sorted(maps.Keys(apps))
+}
 
 // Params are what New needs.
 type Params struct {
@@ -259,6 +224,10 @@ type Params struct {
 	// Core Rule Set's rules (SWW_CORE_RULE_SET_EXCLUSIONS_FILE), "" while
 	// there is none.
 	ExclusionsFile string
+	// Apps are the names of the apps each hostname serves, by hostname in
+	// lowercase (SWW_APPS). A request gets the fixes of its hostname's
+	// apps only, or of every app while Apps is nil.
+	Apps map[string][]string
 }
 
 // The ids of sww's own rules, which an exclusions file may not
@@ -350,13 +319,15 @@ func checkExclusions(exclusions string) error {
 type CoreRuleSet struct {
 	engine    coraza.WAF
 	bodyLimit int64
+	apps      map[string][]string
 }
 
-// New returns the Core Rule Set with the fourteen changes, at params'
+// New returns the Core Rule Set with the six changes and the apps' fixes,
-// paranoia level, without the rules it switches off, reading request
+// at params' paranoia level, without the rules it switches off, reading
-// bodies up to params' limit, and with params' exclusions file loaded
+// request bodies up to params' limit, and with params' exclusions file
-// before the Core Rule Set's rules. An exclusions file is an error if it
+// loaded before the Core Rule Set's rules. An exclusions file is an error
-// cannot be read or does not parse, or if checkExclusions refuses it.
+// if it cannot be read or does not parse, or if checkExclusions refuses
+// it.
 func New(params Params) (*CoreRuleSet, error) {
 	body := ""
 	if params.BodyLimit > 0 {
@@ -379,10 +350,13 @@ func New(params Params) (*CoreRuleSet, error) {
 		}
 	}
 
+	var fixes strings.Builder
+	for _, name := range AppNames() {
+		fixes.WriteString(apps[name].directives + "\n")
+	}
+
 	text := fmt.Sprintf(directives, params.ParanoiaLevel, body, exclusions,
-		giteaExclusions, wordpressExclusions, drupalExclusions,
+		fixes.String())
-		mediawikiExclusions, mastodonExclusions, vaultwardenExclusions,
-		nextcloudExclusions)
 
 	if len(params.DisabledRules) > 0 {
 		ids := make([]string, len(params.DisabledRules))
@@ -400,7 +374,9 @@ func New(params Params) (*CoreRuleSet, error) {
 		return nil, fmt.Errorf("load the Core Rule Set: %w", err)
 	}
 
-	return &CoreRuleSet{engine: engine, bodyLimit: params.BodyLimit}, nil
+	return &CoreRuleSet{
+		engine: engine, bodyLimit: params.BodyLimit, apps: params.Apps,
+	}, nil
 }
 
 // Result is what the Core Rule Set found in a request.
@@ -412,11 +388,12 @@ type Result struct {
 	Score int
 }
 
-// Inspect runs the Core Rule Set on r, a request from client: on its
+// Inspect runs the Core Rule Set on r, a request from client, with the
-// method, its URL with the query, and its headers, the Cookie header
+// fixes of the apps appsFor names for r's hostname: on its method, its URL
-// without the cookies in cookiesNotRead, and on body, r's body as the
+// with the query, and its headers, the Cookie header without those apps'
-// caller has it, as readBody reads it. It returns what it found, what it
+// cookies, and on body, r's body as the caller has it, as readBody reads
-// read of body, and the error that ended the reading early, if one did.
+// it. It returns what it found, what it read of body, and the error that
+// ended the reading early, if one did.
 func (c *CoreRuleSet) Inspect(
 	r *http.Request, client netip.Addr, body io.Reader,
 ) (Result, []byte, error) {
@@ -424,13 +401,24 @@ func (c *CoreRuleSet) Inspect(
 	// Closing would remove the files Coraza wrote, and it writes none.
 	defer func() { _ = tx.Close() }()
 
+	// The transaction's variables are set only through Coraza's interface
+	// for plugins.
+	state := tx.(plugintypes.TransactionState) //nolint:forcetypeassert // every one is
+
+	var cookiesNotRead []string
+
+	for _, name := range c.appsFor(r.Host) {
+		state.Variables().TX().Set("app_"+name, []string{"1"})
+		cookiesNotRead = append(cookiesNotRead, apps[name].cookies...)
+	}
+
 	tx.ProcessConnection(client.String(), 0, "", 0)
 	tx.ProcessURI(r.URL.String(), r.Method, r.Proto)
 
 	for name, values := range r.Header {
 		for _, value := range values {
 			if name == "Cookie" {
-				value = withoutCookiesNotRead(value)
+				value = withoutCookies(value, cookiesNotRead)
 				if value == "" {
 					continue // it held those cookies alone
 				}
@@ -523,9 +511,26 @@ func score(tx types.Transaction) int {
 	return n
 }
 
-// withoutCookiesNotRead returns value, a Cookie header's, without the
+// appsFor returns the names of the apps whose fixes a request for host,
-// cookies in cookiesNotRead.
+// its Host header, gets: every app while SWW_APPS is unset, and otherwise
-func withoutCookiesNotRead(value string) string {
+// those SWW_APPS lists for host's name, without the port and in
+// lowercase.
+func (c *CoreRuleSet) appsFor(host string) []string {
+	if c.apps == nil {
+		return AppNames()
+	}
+
+	hostname, _, err := net.SplitHostPort(host)
+	if err != nil {
+		hostname = host // it has no port
+	}
+
+	return c.apps[strings.ToLower(hostname)]
+}
+
+// withoutCookies returns value, a Cookie header's, without the cookies
+// named in cookiesNotRead.
+func withoutCookies(value string, cookiesNotRead []string) string {
 	var kept []string
 
 	for cookie := range strings.SplitSeq(value, ";") {

internal/coreruleset/coreruleset_test.go

@@ -36,12 +36,14 @@ var loaded = struct {
 }{loaders: map[string]func() (*coreruleset.CoreRuleSet, error){}}
 
 // loaderFor returns the function that loads the Core Rule Set with params
-// once, making it the first time params are asked for.
+// once, making it the first time params are asked for. %#v writes a nil
+// Apps, which gives every app's fixes, apart from an empty one, which
+// gives none.
 func loaderFor(params coreruleset.Params) func() (*coreruleset.CoreRuleSet, error) {
 	loaded.Lock()
 	defer loaded.Unlock()
 
-	settings := fmt.Sprintf("%+v", params)
+	settings := fmt.Sprintf("%#v", params)
 
 	load, found := loaded.loaders[settings]
 	if !found {
@@ -155,9 +157,10 @@ func inspectBody(
 	}
 
 	for _, header := range r.headers {
-		// Go's server keeps Host and Transfer-Encoding out of the headers.
+		// Go's server keeps Host and Transfer-Encoding out of the headers,
+		// whatever their case.
 		name, value, _ := strings.Cut(header, ": ")
-		switch name {
+		switch http.CanonicalHeaderKey(name) {
 		case "Host":
 			req.Host = value
 		case "Transfer-Encoding":
@@ -202,8 +205,8 @@ func atDefaults(t *testing.T) *coreruleset.CoreRuleSet {
 }
 
 // wantChange checks that crs lets through passes, a request one of the
-// fourteen changes is for, and still finds result in refused, a request like
+// six changes or an app's fixes are for, and still finds result in
-// it that the change is not for.
+// refused, a request like it that they are not for.
 func wantChange(
 	t *testing.T, crs *coreruleset.CoreRuleSet, passes, refused request,
 	result coreruleset.Result,
@@ -464,6 +467,123 @@ func TestImagePushThatReusesALayerIsNotCheckedForCommandNames(t *testing.T) {
 		matched(930120, 932160))
 }
 
+// giteaFixed are gitea requests that only gitea's fixes let through, one
+// for each kind of fix, each with what the Core Rule Set finds in it
+// without them.
+//
+//nolint:gochecknoglobals // a constant cannot be a list
+var giteaFixed = []struct {
+	request request
+	result  coreruleset.Result
+}{
+	// A search of code, on the path of gitea's search.
+	{get("/explore/code?q=SELECT%20*%20FROM%20users%20WHERE"), matched(942100)},
+	// A file name, in a parameter gitea sends names in, on any path.
+	{get("/?path=.gitignore"), matched(930120)},
+	// A file name, in a cookie of gitea's.
+	{
+		get("/owner/repo", "Cookie: gitea_flash=success%3DFile%2Bpackage.json%2Bdeleted"),
+		matched(930120),
+	},
+}
+
+// The hostnames of the tests of SWW_APPS: the one that serves gitea, and
+// one that serves another app.
+const (
+	giteaHost = "git.example"
+	otherHost = "blog.example"
+)
+
+// gitea is gitea's name in SWW_APPS.
+const gitea = "gitea"
+
+// wordpress is WordPress's name in SWW_APPS.
+const wordpress = "wordpress"
+
+// withHost returns r sent to host.
+func withHost(r request, host string) request {
+	return request{r.method, r.target, append([]string{"Host: " + host}, r.headers...)}
+}
+
+// servingApps returns the Core Rule Set at the defaults, with SWW_APPS
+// giving apps.
+func servingApps(t *testing.T, apps map[string][]string) *coreruleset.CoreRuleSet {
+	t.Helper()
+
+	return shared(t, coreruleset.Params{
+		ParanoiaLevel: 1, DisabledRules: defaultDisabledRules, Apps: apps,
+	})
+}
+
+func TestAppsUnsetGivesEveryHostnameEveryAppsFixes(t *testing.T) {
+	t.Parallel()
+
+	crs := servingApps(t, nil)
+
+	for _, fixed := range giteaFixed {
+		for _, host := range []string{giteaHost, otherHost} {
+			wantResult(t, crs, withHost(fixed.request, host), coreruleset.Result{})
+		}
+	}
+}
+
+func TestListedHostnameGetsItsAppsFixes(t *testing.T) {
+	t.Parallel()
+
+	crs := servingApps(t, map[string][]string{giteaHost: {gitea}})
+
+	// The hostname is matched without the port and without regard to case.
+	for _, host := range []string{giteaHost, "GIT.Example:8443"} {
+		for _, fixed := range giteaFixed {
+			wantResult(t, crs, withHost(fixed.request, host), coreruleset.Result{})
+		}
+	}
+}
+
+func TestUnlistedHostnameGetsTheFullCheck(t *testing.T) {
+	t.Parallel()
+
+	for _, apps := range []map[string][]string{
+		{giteaHost: {gitea}},
+		// SWW_APPS set empty lists no hostname.
+		{},
+	} {
+		crs := servingApps(t, apps)
+
+		for _, host := range []string{otherHost, otherHost + ":8443", "git.example.org"} {
+			for _, fixed := range giteaFixed {
+				wantResult(t, crs, withHost(fixed.request, host), fixed.result)
+			}
+		}
+	}
+}
+
+func TestWordPressFixesApplyOnlyToAHostnameThatServesWordPress(t *testing.T) {
+	t.Parallel()
+
+	crs := servingApps(t, map[string][]string{
+		giteaHost: {gitea}, otherHost: {wordpress},
+	})
+
+	// A search, which only WordPress's fixes let through.
+	search := get("/?s=python3")
+
+	wantResult(t, crs, withHost(search, otherHost), coreruleset.Result{})
+	wantResult(t, crs, withHost(search, giteaHost), matched(932260))
+}
+
+func TestHostnameListingTwoAppsGetsTheFixesOfBoth(t *testing.T) {
+	t.Parallel()
+
+	crs := servingApps(t, map[string][]string{giteaHost: {gitea, wordpress}})
+
+	// A file name that only gitea's fixes let through, and a search that only
+	// WordPress's fixes let through.
+	for _, target := range []string{"/?path=.gitignore", "/?s=python3"} {
+		wantResult(t, crs, withHost(get(target), giteaHost), coreruleset.Result{})
+	}
+}
+
 // withExclusions returns the Core Rule Set at the defaults, with the
 // exclusions file at path.
 func withExclusions(path string) (*coreruleset.CoreRuleSet, error) {
@@ -625,17 +745,24 @@ const passwordField = "password="
 var hardValues = []string{"python3", "powershell", "ls%20-la", ".htaccess"}
 
 // wantRecordedRequestsPass checks that none of the recorded ordinary
-// requests in the file name in testdata is refused, at the defaults and
+// requests in the file name in testdata is refused on example.com, where
-// while bodies are read. A request with neither a body nor a Content-Type
+// they were recorded, while SWW_APPS lists only app for it. They are
-// header is checked only at the defaults: with neither, the set that reads
+// checked at the defaults and while bodies are read. With SWW_APPS unset,
-// bodies has nothing more to check. Each request runs as its own parallel
+// every app's fixes apply. These only switch checks off, so the requests
-// subtest.
+// pass then too. A request with neither a body nor a Content-Type header is
-func wantRecordedRequestsPass(t *testing.T, name string) {
+// checked only at the defaults: with neither, the set that reads bodies has
+// nothing more to check. Each request runs as its own parallel subtest.
+func wantRecordedRequestsPass(t *testing.T, name, app string) {
 	t.Helper()
 
 	const threshold = 5 // SWW_WAF_ANOMALY_THRESHOLD's default
 
-	defaults, bodies := atDefaults(t), readingBodies(t)
+	apps := map[string][]string{"example.com": {app}}
+	defaults := servingApps(t, apps)
+	bodies := shared(t, coreruleset.Params{
+		ParanoiaLevel: 1, DisabledRules: defaultDisabledRules, BodyLimit: bodyLimit,
+		Apps: apps,
+	})
 
 	for _, recorded := range recordedRequests(t, name) {
 		t.Run(recorded.Method+" "+recorded.Target, func(t *testing.T) {
@@ -671,10 +798,13 @@ func TestOrdinaryGiteaRequestsPassAndAttacksAreRefused(t *testing.T) {
 
 	const threshold = 5 // SWW_WAF_ANOMALY_THRESHOLD's default
 
+	// The recorded requests pass on giteaHost with gitea's fixes alone. The
+	// attacks are refused at the defaults, where every app's fixes apply.
+	giteaOnly := servingApps(t, map[string][]string{giteaHost: {gitea}})
 	crs := atDefaults(t)
 
 	for _, r := range giteaRequests(t) {
-		if got := inspect(t, crs, r); got.Score >= threshold {
+		if got := inspect(t, giteaOnly, withHost(r, giteaHost)); got.Score >= threshold {
 			t.Errorf("%s %q refused: %+v", r.target, r.headers[1:], got)
 		}
 	}
@@ -836,12 +966,22 @@ func wordpressAttackTargets(attack string) []string {
 	}
 }
 
-func TestOrdinaryWordPressRequestsPassAndAttacksAreRefused(t *testing.T) {
+// wantWordPressRequestsPass checks that the recorded ordinary WordPress
-	t.Parallel()
+// requests pass on otherHost, where they were recorded, while SWW_APPS lists
+// only wordpress for it. They pass at the defaults, and those with a body
+// pass while bodies up to 64 KiB are read too. Every app's fixes only switch
+// checks off, so the requests pass with SWW_APPS unset too.
+func wantWordPressRequestsPass(t *testing.T) {
+	t.Helper()
 
 	const threshold = 5 // SWW_WAF_ANOMALY_THRESHOLD's default
 
-	defaults, bodies := atDefaults(t), readingBodiesUpTo64K(t)
+	apps := map[string][]string{otherHost: {wordpress}}
+	defaults := servingApps(t, apps)
+	bodies := shared(t, coreruleset.Params{
+		ParanoiaLevel: 1, DisabledRules: defaultDisabledRules, BodyLimit: 64<<10 - 1,
+		Apps: apps,
+	})
 
 	for _, recorded := range recordedRequests(t, "wordpress-requests.txt") {
 		t.Run(recorded.Method+" "+recorded.Target, func(t *testing.T) {
@@ -862,6 +1002,16 @@ func TestOrdinaryWordPressRequestsPassAndAttacksAreRefused(t *testing.T) {
 			}
 		})
 	}
+}
+
+func TestOrdinaryWordPressRequestsPassAndAttacksAreRefused(t *testing.T) {
+	t.Parallel()
+
+	const threshold = 5 // SWW_WAF_ANOMALY_THRESHOLD's default
+
+	wantWordPressRequestsPass(t)
+
+	defaults, bodies := atDefaults(t), readingBodiesUpTo64K(t)
 
 	for _, attack := range []string{
 		sqlInjection,

internal/coreruleset/drupal.conf

@@ -1,4 +1,4 @@
-# The tenth change: on Drupal's paths, some fields skip the rules that refused
+# Drupal's fixes: on Drupal's paths, some fields skip the rules that refused
 # ordinary Drupal requests there. They are the fields where Drupal sends a
 # search, a name, a file name or an address. Each exclusion runs with the
 # request, before the rules it switches off, so this file is loaded before the
@@ -25,6 +25,13 @@
 #   932230: ls -la
 #   932235: python3
 
+# Unless SWW_APPS lists drupal for the request's hostname, every rule below is
+# skipped. Inspect sets tx.app_drupal when it does.
+# The skip reaches only phase 1, so a rule of a later phase must check
+# tx.app_drupal itself.
+SecRule &TX:app_drupal "@eq 0" \
+    "id:900790,phase:1,pass,nolog,skipAfter:END_DRUPAL"
+
 # Every admin page's filters and autocompletes, and the page to return to:
 #   title: /admin/content?title=python3
 #   name: /admin/content/media?name=python3
@@ -237,3 +244,5 @@ SecRule REQUEST_FILENAME "@rx ^(?:/[a-z]{2,3}(?:-[a-z]+)?)?/user/password$" \
     SecRule &ARGS_GET:json.mail "@eq 0" \
         "ctl:ruleRemoveTargetById=932120;ARGS:json.mail,\
         ctl:ruleRemoveTargetById=932260;ARGS:json.mail"
+
+SecMarker END_DRUPAL

internal/coreruleset/drupal_test.go

@@ -5,6 +5,8 @@ import (
 	"net/url"
 	"slices"
 	"testing"
+
+	"sneak.berlin/go/smallwebwaf/internal/coreruleset"
 )
 
 // drupalThreshold is SWW_WAF_ANOMALY_THRESHOLD's default.
@@ -34,7 +36,21 @@ const drupalName = "name="
 func TestOrdinaryDrupalRequestsPass(t *testing.T) {
 	t.Parallel()
 
-	wantRecordedRequestsPass(t, "drupal-requests.txt")
+	wantRecordedRequestsPass(t, "drupal-requests.txt", "drupal")
+}
+
+func TestDrupalFixesApplyOnlyToAHostnameThatServesDrupal(t *testing.T) {
+	t.Parallel()
+
+	crs := servingApps(t, map[string][]string{
+		giteaHost: {gitea}, otherHost: {"drupal"},
+	})
+
+	// A search, which only Drupal's fixes let through.
+	search := get("/search?keys=python3")
+
+	wantResult(t, crs, withHost(search, otherHost), coreruleset.Result{})
+	wantResult(t, crs, withHost(search, giteaHost), matched(932260))
 }
 
 // drupalAttacks are an SQL injection, a path traversal and a script

internal/coreruleset/gitea.conf

@@ -1,8 +1,55 @@
-# The eighth change: on gitea's paths, some fields skip the rules that refused
+# gitea's fixes: some fields skip the rules that refused ordinary gitea requests.
-# ordinary gitea requests there. They are the fields where gitea sends a search,
+# They are the fields where gitea sends a search, a file name or a branch name.
-# a file name or a branch name. Each exclusion runs with the request, before the
+# Each exclusion runs with the request, before the rules it switches off, those
-# rules it switches off, those of phase 1 included, so this file is loaded before
+# of phase 1 included, so this file is loaded before the Core Rule Set's rules.
-# the Core Rule Set's rules. Each comment names a request the rule refused.
+# Each comment names a request the rule refused.
+
+# Unless SWW_APPS lists gitea for the request's hostname, every rule below is
+# skipped. Inspect sets tx.app_gitea when it does.
+# The skip reaches only phase 1, so a rule of a later phase must check
+# tx.app_gitea itself.
+SecRule &TX:app_gitea "@eq 0" \
+    "id:900590,phase:1,pass,nolog,skipAfter:END_GITEA"
+
+# The query parameters in which gitea sends names within a repository or its
+# own records, or a page of its own site, are not checked against the lists of
+# system files, shell paths and command names, on any path:
+#   930120: .gitignore
+#   932160: bin/docker-entrypoint
+#   932260: docker-build
+# ARGS holds the fields of a form data or multipart body Coraza reads as well
+# as the query parameters, so a field of these names is left out too.
+SecAction "id:900591,phase:1,pass,nolog,\
+    ctl:ruleRemoveTargetById=930120;ARGS:path,\
+    ctl:ruleRemoveTargetById=930120;ARGS:files,\
+    ctl:ruleRemoveTargetById=930120;ARGS:skip-to,\
+    ctl:ruleRemoveTargetById=930120;ARGS:sub_path,\
+    ctl:ruleRemoveTargetById=930120;ARGS:ref,\
+    ctl:ruleRemoveTargetById=930120;ARGS:sha,\
+    ctl:ruleRemoveTargetById=930120;ARGS:branch,\
+    ctl:ruleRemoveTargetById=930120;ARGS:workflow,\
+    ctl:ruleRemoveTargetById=930120;ARGS:artifactName,\
+    ctl:ruleRemoveTargetById=930120;ARGS:redirect_to,\
+    ctl:ruleRemoveTargetById=932160;ARGS:path,\
+    ctl:ruleRemoveTargetById=932160;ARGS:files,\
+    ctl:ruleRemoveTargetById=932160;ARGS:skip-to,\
+    ctl:ruleRemoveTargetById=932160;ARGS:sub_path,\
+    ctl:ruleRemoveTargetById=932160;ARGS:ref,\
+    ctl:ruleRemoveTargetById=932160;ARGS:sha,\
+    ctl:ruleRemoveTargetById=932160;ARGS:branch,\
+    ctl:ruleRemoveTargetById=932160;ARGS:workflow,\
+    ctl:ruleRemoveTargetById=932160;ARGS:artifactName,\
+    ctl:ruleRemoveTargetById=932160;ARGS:redirect_to,\
+    ctl:ruleRemoveTargetById=932260;ARGS:path,\
+    ctl:ruleRemoveTargetById=932260;ARGS:files,\
+    ctl:ruleRemoveTargetById=932260;ARGS:skip-to,\
+    ctl:ruleRemoveTargetById=932260;ARGS:sub_path,\
+    ctl:ruleRemoveTargetById=932260;ARGS:ref,\
+    ctl:ruleRemoveTargetById=932260;ARGS:sha,\
+    ctl:ruleRemoveTargetById=932260;ARGS:branch,\
+    ctl:ruleRemoveTargetById=932260;ARGS:workflow,\
+    ctl:ruleRemoveTargetById=932260;ARGS:artifactName,\
+    ctl:ruleRemoveTargetById=932260;ARGS:redirect_to"
 
 # gitea's searches of code, of issues and pull requests, and of commits send the
 # text searched for in q, which skips these rules there:
@@ -163,8 +210,8 @@ SecRule REQUEST_FILENAME \
 #   942140: information_schema.sql
 #   944110: java/lang/Runtime.java
 #   944130: java.lang.String.md
-# Each request skips the rules that refused it. The fourth change already has
+# Each request skips the rules that refused it. Rule 900591 already has path and
-# path and redirect_to skip 930120, 932160 and 932260 on every path.
+# redirect_to skip 930120, 932160 and 932260 on every path.
 
 # A file's commit graph, in file.
 SecRule REQUEST_FILENAME "@rx ^/[^/]+/[^/]+/graph$" \
@@ -289,3 +336,5 @@ SecRule REQUEST_FILENAME \
     "@rx ^/api/actions_pipeline/_apis/pipelines/workflows/[0-9]+/artifacts/[^/]+/upload$" \
     "id:900640,phase:1,pass,nolog,\
     ctl:ruleRemoveTargetById=920450;REQUEST_HEADERS_NAMES:Content-Range"
+
+SecMarker END_GITEA

internal/coreruleset/mastodon.conf

@@ -1,4 +1,4 @@
-# The twelfth change: on Mastodon's paths, some fields skip the rules that
+# Mastodon's fixes: on Mastodon's paths, some fields skip the rules that
 # refused ordinary Mastodon requests there. They are the fields where Mastodon
 # sends a search, a name, a title, a file name, an address or free text. Each
 # exclusion runs with the request, before the rules it switches off, so this
@@ -17,6 +17,13 @@
 #   932250: ls -la
 #   932260: python3
 
+# Unless SWW_APPS lists mastodon for the request's hostname, every rule below is
+# skipped. Inspect sets tx.app_mastodon when it does.
+# The skip reaches only phase 1, so a rule of a later phase must check
+# tx.app_mastodon itself.
+SecRule &TX:app_mastodon "@eq 0" \
+    "id:900940,phase:1,pass,nolog,skipAfter:END_MASTODON"
+
 # The API's searches and names, in the query:
 #   q: /api/v2/search?q=python3, /api/v1/accounts/search?q=ls+-la
 #   acct: /api/v1/accounts/lookup?acct=python3
@@ -216,3 +223,5 @@ SecRule REQUEST_FILENAME "@rx ^/auth(?:/|$)" \
         "ctl:ruleRemoveTargetById=930120;ARGS:/^user\[email\]$/,\
         ctl:ruleRemoveTargetById=932120;ARGS:/^user\[email\]$/,\
         ctl:ruleRemoveTargetById=932260;ARGS:/^user\[email\]$/"
+
+SecMarker END_MASTODON

internal/coreruleset/mastodon_test.go

@@ -57,7 +57,21 @@ const (
 func TestOrdinaryMastodonRequestsPass(t *testing.T) {
 	t.Parallel()
 
-	wantRecordedRequestsPass(t, "mastodon-requests.txt")
+	wantRecordedRequestsPass(t, "mastodon-requests.txt", "mastodon")
+}
+
+func TestMastodonFixesApplyOnlyToAHostnameThatServesMastodon(t *testing.T) {
+	t.Parallel()
+
+	crs := servingApps(t, map[string][]string{
+		giteaHost: {gitea}, otherHost: {"mastodon"},
+	})
+
+	// A search, which only Mastodon's fixes let through.
+	search := get("/api/v2/search?q=python3")
+
+	wantResult(t, crs, withHost(search, otherHost), coreruleset.Result{})
+	wantResult(t, crs, withHost(search, giteaHost), matched(932260))
 }
 
 // mastodonQueryFields sends each field that skips 930120, 932120, 932250

internal/coreruleset/mediawiki.conf

@@ -1,4 +1,4 @@
-# The eleventh change: on MediaWiki's paths, some fields skip the rules that
+# MediaWiki's fixes: on MediaWiki's paths, some fields skip the rules that
 # refused ordinary MediaWiki requests there. They are the fields where MediaWiki
 # sends a search, a title, a name, a file name, an address, a summary or a
 # reason, and the fields that hold wikitext. Each exclusion runs with the
@@ -21,6 +21,13 @@
 #   932250: ls -la
 #   932260: python3
 
+# Unless SWW_APPS lists mediawiki for the request's hostname, every rule below
+# is skipped. Inspect sets tx.app_mediawiki when it does.
+# The skip reaches only phase 1, so a rule of a later phase must check
+# tx.app_mediawiki itself.
+SecRule &TX:app_mediawiki "@eq 0" \
+    "id:900890,phase:1,pass,nolog,skipAfter:END_MEDIAWIKI"
+
 # The pages and their titles, the searches, and the special pages' fields
 # for a page, a user, a file or an address:
 #   title: /index.php?title=Python3_notes&action=history
@@ -198,10 +205,12 @@ SecRule REQUEST_FILENAME "@rx ^/(?:w/)?index\.php(?:$|/.)|^/wiki/" \
 # This rule is in phase 2, because a phase 1 rule runs before the body is read
 # and cannot see what wpTitles holds. It checks that the body sends wpTitles
 # once, since it would otherwise skip these rules for a second wpTitles
-# holding a command.
+# holding a command. It checks tx.app_mediawiki, since the skip above does not
+# reach phase 2.
 SecRule REQUEST_FILENAME "@rx ^/(?:w/)?index\.php(?:$|/.)|^/wiki/" \
     "id:900916,phase:2,pass,nolog,chain"
     SecRule REQUEST_FILENAME|ARGS_GET_NAMES "@rx ^/(?:w/)?index\.php/.|^/wiki/|^title$" "chain"
+    SecRule &TX:app_mediawiki "@eq 1" "chain"
     SecRule &ARGS_GET:wpTitles "@eq 0" "chain"
     SecRule &ARGS_POST:wpTitles "@eq 1" "chain"
     SecRule ARGS_POST:wpTitles "!@rx [;|&`{]" \
@@ -210,3 +219,5 @@ SecRule REQUEST_FILENAME "@rx ^/(?:w/)?index\.php(?:$|/.)|^/wiki/" \
         ctl:ruleRemoveTargetById=932235;ARGS:wpTitles,\
         ctl:ruleRemoveTargetById=932260;ARGS:wpTitles,\
         ctl:ruleRemoveTargetById=932380;ARGS:wpTitles"
+
+SecMarker END_MEDIAWIKI

internal/coreruleset/mediawiki_test.go

@@ -4,11 +4,16 @@ import (
 	"net/http"
 	"slices"
 	"testing"
+
+	"sneak.berlin/go/smallwebwaf/internal/coreruleset"
 )
 
 // mediawikiThreshold is SWW_WAF_ANOMALY_THRESHOLD's default.
 const mediawikiThreshold = 5
 
+// mediawiki is MediaWiki's name in SWW_APPS.
+const mediawiki = "mediawiki"
+
 // mediawikiEdit is the address MediaWiki's edit form posts to.
 const mediawikiEdit = "/index.php?title=Example&action=submit"
 
@@ -45,7 +50,44 @@ const (
 func TestOrdinaryMediaWikiRequestsPass(t *testing.T) {
 	t.Parallel()
 
-	wantRecordedRequestsPass(t, "mediawiki-requests.txt")
+	wantRecordedRequestsPass(t, "mediawiki-requests.txt", mediawiki)
+}
+
+func TestMediaWikiFixesApplyOnlyToAHostnameThatServesMediaWiki(t *testing.T) {
+	t.Parallel()
+
+	crs := servingApps(t, map[string][]string{
+		giteaHost: {gitea}, otherHost: {mediawiki},
+	})
+
+	// A search, which only MediaWiki's fixes let through.
+	search := get("/index.php?title=Special:Search&search=python3")
+
+	wantResult(t, crs, withHost(search, otherHost), coreruleset.Result{})
+	wantResult(t, crs, withHost(search, giteaHost), matched(932260))
+}
+
+func TestMediaWikiWatchlistFixAppliesOnlyToAHostnameThatServesMediaWiki(t *testing.T) {
+	t.Parallel()
+
+	crs := shared(t, coreruleset.Params{
+		ParanoiaLevel: 1, DisabledRules: defaultDisabledRules, BodyLimit: bodyLimit,
+		Apps: map[string][]string{giteaHost: {gitea}, otherHost: {mediawiki}},
+	})
+
+	// A watchlist that only the phase 2 rule 900916 lets through.
+	r := request{http.MethodPost, mediawikiWatchlist.target, []string{formData}}
+	body := mediawikiWatchlist.field + "Lighthouse%20notes%0D%0APython3%20notes"
+
+	got, _ := inspectBody(t, crs, withHost(r, otherHost), body)
+	if got.Score >= mediawikiThreshold {
+		t.Errorf("POST %s %s on %s refused: %+v", r.target, body, otherHost, got)
+	}
+
+	got, _ = inspectBody(t, crs, withHost(r, giteaHost), body)
+	if got.Score < mediawikiThreshold {
+		t.Errorf("POST %s %s on %s let through: %+v", r.target, body, giteaHost, got)
+	}
 }
 
 // mediawikiQueryFields and mediawikiBodyFields together hold every field that

internal/coreruleset/nextcloud.conf

@@ -1,4 +1,4 @@
-# The fourteenth change: on Nextcloud's paths, some fields skip the rules that
+# Nextcloud's fixes: on Nextcloud's paths, some fields skip the rules that
 # refused ordinary Nextcloud requests there. They are the fields where Nextcloud
 # sends a search, a name, a file name, a folder, a comment, a note, a status or
 # a document's text. Each exclusion runs with the request, before the rules it
@@ -29,6 +29,13 @@
 # "; wget http://example.com/x.sh" reaches Nextcloud in these fields. SQL
 # injection, path traversal and script injection are still refused there.
 
+# Unless SWW_APPS lists nextcloud for the request's hostname, every rule below
+# is skipped. Inspect sets tx.app_nextcloud when it does.
+# The skip reaches only phase 1, so a rule of a later phase must check
+# tx.app_nextcloud itself.
+SecRule &TX:app_nextcloud "@eq 0" \
+    "id:900090,phase:1,pass,nolog,skipAfter:END_NEXTCLOUD"
+
 # The sync client and the Files app use these WebDAV methods besides those
 # the first change allows, on /remote.php/dav/ and /public.php/dav/ and on the
 # older /remote.php/webdav/ and /public.php/webdav/. 911100 refused each:
@@ -306,3 +313,5 @@ SecRule REQUEST_FILENAME "@rx ^/remote\.php/dav/addressbooks/" \
     SecRule REQUEST_METHOD "@streq MKCOL" \
         "ctl:ruleRemoveTargetById=932125;XML:/*,\
         ctl:ruleRemoveTargetById=932230;XML:/*"
+
+SecMarker END_NEXTCLOUD

internal/coreruleset/nextcloud_test.go

@@ -48,10 +48,47 @@ const (
 // nextcloudOther is a JSON field no exclusion names.
 const nextcloudOther = `{"other":"python3"}`
 
+// nextcloud is Nextcloud's name in SWW_APPS.
+const nextcloud = "nextcloud"
+
 func TestOrdinaryNextcloudRequestsPass(t *testing.T) {
 	t.Parallel()
 
-	wantRecordedRequestsPass(t, "nextcloud-requests.txt")
+	wantRecordedRequestsPass(t, "nextcloud-requests.txt", nextcloud)
+}
+
+func TestNextcloudFixesApplyOnlyToAHostnameThatServesNextcloud(t *testing.T) {
+	t.Parallel()
+
+	crs := servingApps(t, map[string][]string{
+		giteaHost: {gitea}, otherHost: {nextcloud},
+	})
+
+	// A search, which only Nextcloud's fixes let through.
+	search := get(nextcloudUsers + "?search=python3")
+
+	wantResult(t, crs, withHost(search, otherHost), coreruleset.Result{})
+	wantResult(t, crs, withHost(search, giteaHost), matched(932260))
+}
+
+func TestNextcloudWebDAVMethodsPassOnlyOnHostnamesThatServeNextcloud(t *testing.T) {
+	t.Parallel()
+
+	crs := servingApps(t, map[string][]string{
+		giteaHost: {gitea}, otherHost: {nextcloud},
+	})
+
+	// Listing a folder, as the sync client does.
+	list := request{nextcloudPropFind, nextcloudFiles, nil}
+
+	wantResult(t, crs, withHost(list, otherHost), coreruleset.Result{})
+	wantResult(t, crs, withHost(list, giteaHost), matched(911100))
+
+	// Making a calendar, as a CalDAV client does.
+	calendar := request{nextcloudMkcalendar, nextcloudCalendars + "work/", nil}
+
+	wantResult(t, crs, withHost(calendar, otherHost), coreruleset.Result{})
+	wantResult(t, crs, withHost(calendar, giteaHost), matched(911100))
 }
 
 // nextcloudQueryFields are the query fields that skip 930120, 932120, 932250

internal/coreruleset/vaultwarden.conf

@@ -1,4 +1,4 @@
-# The thirteenth change: on Vaultwarden's paths, some fields skip the rules that
+# Vaultwarden's fixes: on Vaultwarden's paths, some fields skip the rules that
 # refused ordinary Vaultwarden requests there. They are the fields where
 # Vaultwarden receives a name, a password hint or an email address in plain
 # text, and the names of uploaded files. Each exclusion runs with the request,
@@ -17,6 +17,13 @@
 #   932250: ls -la
 #   932260: python3
 
+# Unless SWW_APPS lists vaultwarden for the request's hostname, every rule below
+# is skipped. Inspect sets tx.app_vaultwarden when it does.
+# The skip reaches only phase 1, so a rule of a later phase must check
+# tx.app_vaultwarden itself.
+SecRule &TX:app_vaultwarden "@eq 0" \
+    "id:900140,phase:1,pass,nolog,skipAfter:END_VAULTWARDEN"
+
 # Names and password hints, in JSON bodies, skip the four rules:
 #   name: signing up, editing the account's profile, and creating or renaming
 #   an organization or a group, "python3 .htaccess team"
@@ -82,3 +89,5 @@ SecRule REQUEST_FILENAME "@rx ^/api/hibp/breach$" \
 SecRule REQUEST_FILENAME "@rx ^/api/ciphers/[0-9a-f-]{36}/attachment(?:-admin|/[0-9a-f]+(?:/share)?)?$|^/api/sends/[0-9a-f-]{36}/file/[0-9a-f]+$" \
     "id:900153,phase:1,pass,nolog,\
     ctl:ruleRemoveTargetById=920120;FILES"
+
+SecMarker END_VAULTWARDEN

internal/coreruleset/vaultwarden_test.go

@@ -7,6 +7,8 @@ import (
 	"slices"
 	"strings"
 	"testing"
+
+	"sneak.berlin/go/smallwebwaf/internal/coreruleset"
 )
 
 // vaultwardenThreshold is SWW_WAF_ANOMALY_THRESHOLD's default.
@@ -30,7 +32,22 @@ const vaultwardenEmail = `{"email":"VALUE"}`
 func TestOrdinaryVaultwardenRequestsPass(t *testing.T) {
 	t.Parallel()
 
-	wantRecordedRequestsPass(t, "vaultwarden-requests.txt")
+	wantRecordedRequestsPass(t, "vaultwarden-requests.txt", "vaultwarden")
+}
+
+func TestVaultwardenFixesApplyOnlyToAHostnameThatServesVaultwarden(t *testing.T) {
+	t.Parallel()
+
+	crs := servingApps(t, map[string][]string{
+		giteaHost: {gitea}, otherHost: {"vaultwarden"},
+	})
+
+	// An address for the data breach report, which only Vaultwarden's fixes
+	// let through.
+	report := get(vaultwardenBreachReport + "python3%40example.com")
+
+	wantResult(t, crs, withHost(report, otherHost), coreruleset.Result{})
+	wantResult(t, crs, withHost(report, giteaHost), matched(932260))
 }
 
 // vaultwardenField is a field Vaultwarden receives in plain text: the

internal/coreruleset/wordpress.conf

@@ -1,10 +1,17 @@
-# The ninth change: on WordPress's paths, some fields skip the rules that refused
+# WordPress's fixes: on WordPress's paths, some fields skip the rules that refused
 # ordinary WordPress requests there. Each exclusion runs with the request, before
 # the rules it switches off, so this file is loaded before the Core Rule Set's
 # rules. Each comment names a request the rule refused. An exclusion on a field
 # of a body applies only when the query has no parameter of that name, so it
 # matters only while SWW_WAF_BODY_LIMIT is set.
 
+# Unless SWW_APPS lists wordpress for the request's hostname, every rule below is
+# skipped. Inspect sets tx.app_wordpress when it does.
+# The skip reaches only phase 1, so a rule of a later phase must check
+# tx.app_wordpress itself.
+SecRule &TX:app_wordpress "@eq 0" \
+    "id:900690,phase:1,pass,nolog,skipAfter:END_WORDPRESS"
+
 # WordPress takes a call to its REST API at any of four addresses:
 #   /wp-json/wp/v2/posts/1
 #   /index.php/wp-json/wp/v2/posts/1
@@ -195,3 +202,5 @@ SecRule REQUEST_FILENAME "@rx ^/(?:(?:index\.php/)?page/[0-9]+/?|index\.php)?$"
 # so skips 932340 there.
 SecRule REQUEST_FILENAME "@streq /wp-admin/upload.php" \
     "id:900711,phase:1,pass,nolog,ctl:ruleRemoveTargetById=932340;ARGS:_wp_http_referer"
+
+SecMarker END_WORDPRESS

internal/discriminator/coreruleset_test.go

@@ -10,6 +10,7 @@ import (
 	"testing"
 
 	"sneak.berlin/go/smallwebwaf/internal/alerts"
+	"sneak.berlin/go/smallwebwaf/internal/discriminator"
 	"sneak.berlin/go/smallwebwaf/internal/ratelimit"
 	"sneak.berlin/go/smallwebwaf/internal/requestlog"
 )
@@ -21,6 +22,7 @@ const (
 	wafDisabledRules    = "SWW_WAF_DISABLED_RULES"
 	wafExemptPaths      = "SWW_WAF_EXEMPT_PATHS"
 	wafBodyLimit        = "SWW_WAF_BODY_LIMIT"
+	apps                = "SWW_APPS"
 	block               = "block"
 	detect              = "detect"
 )
@@ -290,6 +292,27 @@ func TestDisabledRulesSwitchOffWhatGiteaWouldBeRefused(t *testing.T) {
 	}
 }
 
+func TestGiteasFixesApplyOnlyToAHostnameThatServesGitea(t *testing.T) {
+	t.Parallel()
+
+	// Only gitea's fixes let a file name through in path, a parameter
+	// gitea sends file names in.
+	const fileName = "/?path=.gitignore"
+
+	s := startDiscriminator(t, "", map[string]string{
+		wafMode: block, apps: siteA + ":gitea",
+	})
+
+	wantDisposition(t, do(t, s.question(siteA, client, fileName)),
+		http.StatusOK, discriminator.DispositionAllow)
+	wantDisposition(t, do(t, s.question(siteB, client, fileName)),
+		http.StatusForbidden, discriminator.DispositionDeny)
+
+	lines := s.out.requestLines(t, 2)
+	wantLine(t, lines[0], http.StatusOK, requestlog.ActionForward)
+	wantLine(t, lines[1], http.StatusForbidden, requestlog.ActionBlockedByCoreRuleSet)
+}
+
 func TestAttackInAFormBodyIsRefusedOnlyWhileBodiesAreRead(t *testing.T) {
 	t.Parallel()
 

internal/discriminator/proxy.go

@@ -221,7 +221,8 @@ func newReputation(
 // NewCoreRuleSet returns the Core Rule Set at SWW_WAF_PARANOIA_LEVEL,
 // without the rules SWW_WAF_DISABLED_RULES switches off, reading bodies
 // up to SWW_WAF_BODY_LIMIT, with the exclusions in
-// SWW_CORE_RULE_SET_EXCLUSIONS_FILE, or nil while SWW_WAF_MODE is off. It
+// SWW_CORE_RULE_SET_EXCLUSIONS_FILE and the fixes of the apps in SWW_APPS,
+// or nil while SWW_WAF_MODE is off. It
 // reads at most QuestionBodyMaxBytes less one byte: a question's body of
 // QuestionBodyMaxBytes may be cut short, and the Core Rule Set does not read a
 // JSON or XML body over its limit. An exclusions file that coreruleset.New refuses is
@@ -236,6 +237,7 @@ func NewCoreRuleSet(cfg *config.Config) (*coreruleset.CoreRuleSet, error) {
 		ParanoiaLevel: cfg.WAFParanoiaLevel, DisabledRules: cfg.WAFDisabledRules,
 		BodyLimit:      min(cfg.WAFBodyLimit, QuestionBodyMaxBytes-1),
 		ExclusionsFile: cfg.CoreRuleSetExclusionsFile,
+		Apps:           cfg.Apps,
 	})
 	if err != nil {
 		return nil, fmt.Errorf("SWW_CORE_RULE_SET_EXCLUSIONS_FILE: %w", err)