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

gitea's fixes (its parameters, its cookies and gitea.conf) now apply
only to a hostname SWW_APPS lists gitea for, or to every hostname while
it is unset. Each app's fixes are one .conf file, whose first rule skips
the rest unless Inspect sets tx.app_<name>, and one entry in apps.

Model: opus-5-5

internal/waf/gitea.conf

@@ -1,8 +1,51 @@
-# The eighth change: on gitea's paths, some fields skip the rules that refused
-# ordinary gitea requests there. They are the fields where gitea sends a search,
-# a file name or a branch name. Each exclusion runs with the request, before the
-# rules it switches off, those of phase 1 included, so this file is loaded before
-# the Core Rule Set's rules. Each comment names a request the rule refused.
+# gitea's fixes: some fields skip the rules that refused ordinary gitea requests.
+# They are the fields where gitea sends a search, a file name or a branch name.
+# Each exclusion runs with the request, before the rules it switches off, those
+# of phase 1 included, so this file is loaded before the Core Rule Set's rules.
+# Each comment names a request the rule refused.
+
+# A request whose hostname SWW_APPS does not list gitea for skips every rule
+# below. Inspect sets tx.app_gitea on the others.
+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
+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:
@@ -155,8 +198,8 @@ 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
-# path and redirect_to skip 930120, 932160 and 932260 on every path.
+# Each request skips the rules that refused it. Rule 900591 already has path and
+# redirect_to skip 930120, 932160 and 932260 on every path.
 
 # A file's commit graph, in file.
 SecRule REQUEST_FILENAME "@rx ^/[^/]+/[^/]+/graph$" \
@@ -281,3 +324,5 @@ SecRule REQUEST_FILENAME \
     "@rx ^/api/actions_pipeline/_apis/pipelines/workflows/[0-9]+/artifacts/[^/]+/upload$" \
     "id:900640,phase:1,pass,nolog,\
     ctl:ruleRemoveTargetById=920450;REQUEST_HEADERS_NAMES:Content-Range"
+
+SecMarker END_GITEA

internal/waf/waf.go

@@ -1,9 +1,9 @@
 // Package waf 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 eight changes sww
-// makes to it and the exclusions in SWW_CORE_RULE_SET_EXCLUSIONS_FILE, as
-// "Attack detection" under "Settings" in SPEC.md describes them. It reads no
-// response.
+// body while SWW_WAF_BODY_LIMIT is set, with the six changes sww
+// makes to it, the fixes for the apps SWW_APPS names, and the exclusions in
+// SWW_CORE_RULE_SET_EXCLUSIONS_FILE, as "Attack detection" under "Settings"
+// 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"
@@ -32,8 +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, and
-// giteaExclusions for the third.
+// SWW_WAF_BODY_LIMIT is set, the exclusions file for the second, and the
+// directives of every app in apps for the third.
 // 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
@@ -81,44 +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 sixth: only the rules for requests are loaded, and no response is
+# The fifth: 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,
-# without regard to case. ARGS holds the fields of a form data or multipart
-# body Coraza reads as well as the query parameters, so a field of one of
-# these names is left out too.
+# localhost. Coraza matches a parameter name here without regard to case.
+# ARGS holds the fields of a form data or multipart body Coraza reads as
+# well as the query parameters, so a field of this name 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
-# 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. 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.
+# The fourth: Referer 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.
 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.
@@ -168,18 +154,36 @@ 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
-// requests that skip the rules that refused them there, as Coraza
-// directives.
-//
-//go:embed gitea.conf
-var giteaExclusions string
+// app is an app whose ordinary requests the Core Rule Set would refuse,
+// with the fixes that let them pass.
+type app struct {
+	// directives are Coraza exclusions, loaded before the Core Rule Set's
+	// rules. Their first rule skips the rest unless Inspect sets the
+	// transaction variable app_ and the app's name, and they end with the
+	// marker it skips to.
+	directives string
+	// cookies are the cookies the Core Rule Set reads a request without.
+	cookies []string
+}
 
-// cookiesNotRead are the cookies the Core Rule Set reads a request
-// without, the rest of the fifth change.
+//go:embed gitea.conf
+var giteaDirectives string
+
+// apps are the apps whose fixes sww has, by the name SWW_APPS gives each.
 //
-//nolint:gochecknoglobals // a constant cannot be a list
-var cookiesNotRead = []string{"gitea_flash", "redirect_to"}
+//nolint:gochecknoglobals // a constant cannot be a map
+var apps = map[string]app{
+	"gitea": {
+		directives: giteaDirectives,
+		cookies:    []string{"gitea_flash", "redirect_to"},
+	},
+}
+
+// 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 {
@@ -195,6 +199,10 @@ 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
@@ -286,13 +294,15 @@ func checkExclusions(exclusions string) error {
 type CoreRuleSet struct {
 	waf       coraza.WAF
 	bodyLimit int64
+	apps      map[string][]string
 }
 
-// New returns the Core Rule Set with the eight changes, at params'
-// paranoia level, without the rules it switches off, reading request
-// bodies up to params' limit, and with params' exclusions file loaded
-// before the Core Rule Set's rules. An exclusions file is an error if it
-// cannot be read or does not parse, or if checkExclusions refuses it.
+// New returns the Core Rule Set with the six changes and the apps' fixes,
+// at params' paranoia level, without the rules it switches off, reading
+// request bodies up to params' limit, and with params' exclusions file
+// loaded before the Core Rule Set's rules. An exclusions file is an error
+// 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 {
@@ -315,8 +325,13 @@ 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)
+		fixes.String())
 
 	if len(params.DisabledRules) > 0 {
 		ids := make([]string, len(params.DisabledRules))
@@ -334,7 +349,7 @@ func New(params Params) (*CoreRuleSet, error) {
 		return nil, fmt.Errorf("load the Core Rule Set: %w", err)
 	}
 
-	return &CoreRuleSet{waf: waf, bodyLimit: params.BodyLimit}, nil
+	return &CoreRuleSet{waf: waf, bodyLimit: params.BodyLimit, apps: params.Apps}, nil
 }
 
 // Result is what the Core Rule Set found in a request.
@@ -346,11 +361,12 @@ type Result struct {
 	Score int
 }
 
-// Inspect runs the Core Rule Set on r, a request from client: on its
-// method, its URL with the query, and its headers, the Cookie header
-// without the cookies in cookiesNotRead, and on body, r's body as the
-// caller has it, as readBody reads it. It returns what it found, what it
-// read of body, and the error that ended the reading early, if one did.
+// Inspect runs the Core Rule Set on r, a request from client, with the
+// fixes of the apps appsFor names for r's hostname: on its method, its URL
+// with the query, and its headers, the Cookie header without those apps'
+// cookies, and on body, r's body as the caller has it, as readBody reads
+// 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) {
@@ -358,13 +374,24 @@ 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
 				}
@@ -457,9 +484,26 @@ func score(tx types.Transaction) int {
 	return n
 }
 
-// withoutCookiesNotRead returns value, a Cookie header's, without the
-// cookies in cookiesNotRead.
-func withoutCookiesNotRead(value string) string {
+// appsFor returns the names of the apps whose fixes a request for host,
+// its Host header, gets: every app while SWW_APPS is unset, and otherwise
+// 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/waf/waf_test.go

@@ -120,8 +120,8 @@ func atDefaults(t *testing.T) *waf.CoreRuleSet {
 }
 
 // wantChange checks that crs lets through passes, a gitea request one of
-// the eight changes is for, and still finds result in refused, a request
-// like it that the change is not for.
+// the six changes or gitea's fixes are for, and still finds result in
+// refused, a request like it that they are not for.
 func wantChange(
 	t *testing.T, crs *waf.CoreRuleSet, passes, refused request, result waf.Result,
 ) {
@@ -381,6 +381,96 @@ 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  waf.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"
+)
+
+// 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) *waf.CoreRuleSet {
+	t.Helper()
+
+	crs, err := waf.New(waf.Params{
+		ParanoiaLevel: 1, DisabledRules: defaultDisabledRules, Apps: apps,
+	})
+	if err != nil {
+		t.Fatalf("load the Core Rule Set: %v", err)
+	}
+
+	return crs
+}
+
+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), waf.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), waf.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)
+			}
+		}
+	}
+}
+
 // withExclusions returns the Core Rule Set at the defaults, with the
 // exclusions file at path.
 func withExclusions(path string) (*waf.CoreRuleSet, error) {