Gitea setup: Core Rule Set blocks attacks, not ordinary Gitea traffic (closes #198)

The Gitea setup runs the Core Rule Set in block mode. Rules that refused ordinary Gitea requests are switched off only where they misfired: - deploy/gitea/crs-exclusions.conf, loaded through the new setting SWWAF_CORE_RULE_SET_EXCLUSIONS_FILE before the Core Rule Set's rules, covers Gitea's search, file-name and branch-name fields, Referer, file paths, API attachment names and Actions artifact uploads; - smallwebwaf's defaults gain a seventh change: the registry upload path's from parameter skips 932260. A file that cannot be read, does not parse or names an id from 900000 to 900999 stops servewaf at start, in every mode. internal/waf's tests and script/gitea-setup send the recorded requests in internal/waf/testdata/gitea-requests.txt and three attacks. Model: opus-5-5
2026-11-06 20:17:07 +00:00
1 parent 21cac70b50
commit 866b948ec0
@@ -221,12 +221,15 @@ type Config struct {
 	// WAFExemptPaths the path prefixes it does not inspect
 	// (SWWAF_WAF_EXEMPT_PATHS), and WAFBodyLimit the most of a request body
 	// it reads (SWWAF_WAF_BODY_LIMIT), 0 while it is off and it reads none.
-	WAFMode             string
-	WAFParanoiaLevel    int
-	WAFAnomalyThreshold int
-	WAFDisabledRules    []int
-	WAFExemptPaths      []string
-	WAFBodyLimit        int64
+	// CoreRuleSetExclusionsFile is the path of the file of its exclusions
+	// (SWWAF_CORE_RULE_SET_EXCLUSIONS_FILE), "" while there is none.
+	WAFMode                   string
+	WAFParanoiaLevel          int
+	WAFAnomalyThreshold       int
+	WAFDisabledRules          []int
+	WAFExemptPaths            []string
+	WAFBodyLimit              int64
+	CoreRuleSetExclusionsFile string
 	// TrapPaths are the paths a request for which is a clear sign of
 	// attack (SWWAF_TRAP_PATHS), each starting with / and without a ?.
 	TrapPaths []string
@@ -523,8 +526,10 @@ func FromEnvironment(lookupEnv func(string) (string, bool)) (*Config, error) {
 		WAFAnomalyThreshold: env.numberOrOff("SWWAF_WAF_ANOMALY_THRESHOLD", "5"),
 		WAFDisabledRules: env.ruleIDs("SWWAF_WAF_DISABLED_RULES",
 			"920340,920420,920440,920640,930130,930140"),
-		WAFExemptPaths:       env.pathPrefixes("SWWAF_WAF_EXEMPT_PATHS", ""),
-		WAFBodyLimit:         env.wafBodyLimit("SWWAF_WAF_BODY_LIMIT", off),
+		WAFExemptPaths: env.pathPrefixes("SWWAF_WAF_EXEMPT_PATHS", ""),
+		WAFBodyLimit:   env.wafBodyLimit("SWWAF_WAF_BODY_LIMIT", off),
+		CoreRuleSetExclusionsFile: env.filePath(
+			"SWWAF_CORE_RULE_SET_EXCLUSIONS_FILE"),
 		TrapPaths:            env.trapPaths("SWWAF_TRAP_PATHS"),
 		ErrorBurstThreshold:  env.count("SWWAF_ERROR_BURST_THRESHOLD", "30"),
 		LogRemoteURL:         env.logRemoteURL("SWWAF_LOG_REMOTE_URL"),
@@ -1189,6 +1194,16 @@ func (e *environment) logRemoteURL(name string) *url.URL {
 	return remote
 }

+// filePath reads a setting that is the path of a file, "" while it is
+// unset. Its value names a file already, so, unlike the other settings,
+// it has no _FILE form. Whoever uses the file reads it.
+func (e *environment) filePath(name string) string {
+	path, _ := e.lookupEnv(name)
+	e.settings = append(e.settings, slog.String(name, path))
+
+	return path
+}
+
 // certificates reads a setting that is the path of a file of PEM
 // certificates. Unset or empty, it is nil. Its value names a file
 // already, so, unlike the other settings, it has no _FILE form.
@@ -87,6 +87,7 @@ const (
 	wafDisabledRules     = "SWWAF_WAF_DISABLED_RULES"
 	wafExemptPaths       = "SWWAF_WAF_EXEMPT_PATHS"
 	wafBodyLimit         = "SWWAF_WAF_BODY_LIMIT"
+	exclusionsFile       = "SWWAF_CORE_RULE_SET_EXCLUSIONS_FILE"
 	trapPaths            = "SWWAF_TRAP_PATHS"
 	errorBurstThreshold  = "SWWAF_ERROR_BURST_THRESHOLD"
 	logRemoteURL         = "SWWAF_LOG_REMOTE_URL"
@@ -539,13 +540,14 @@ func TestCoreRuleSetSettings(t *testing.T) {
 			environment{
 				wafMode: config.WAFModeDetect, wafParanoiaLevel: "4", wafAnomalyThreshold: "10",
 				wafDisabledRules: "942100, 920350", wafExemptPaths: "/api/, /static/",
-				wafBodyLimit: "32K",
+				wafBodyLimit: "32K", exclusionsFile: "/etc/smallwebwaf/crs-exclusions.conf",
 			},
 			config.Config{
 				WAFMode: config.WAFModeDetect, WAFParanoiaLevel: 4, WAFAnomalyThreshold: 10,
-				WAFDisabledRules: []int{942100, 920350},
-				WAFExemptPaths:   []string{"/api/", "/static/"},
-				WAFBodyLimit:     32 << 10,
+				WAFDisabledRules:          []int{942100, 920350},
+				WAFExemptPaths:            []string{"/api/", "/static/"},
+				WAFBodyLimit:              32 << 10,
+				CoreRuleSetExclusionsFile: "/etc/smallwebwaf/crs-exclusions.conf",
 			},
 		},
 		{
@@ -565,7 +567,8 @@ func TestCoreRuleSetSettings(t *testing.T) {
 			WAFMode: cfg.WAFMode, WAFParanoiaLevel: cfg.WAFParanoiaLevel,
 			WAFAnomalyThreshold: cfg.WAFAnomalyThreshold,
 			WAFDisabledRules:    cfg.WAFDisabledRules, WAFExemptPaths: cfg.WAFExemptPaths,
-			WAFBodyLimit: cfg.WAFBodyLimit,
+			WAFBodyLimit:              cfg.WAFBodyLimit,
+			CoreRuleSetExclusionsFile: cfg.CoreRuleSetExclusionsFile,
 		}
 		if !reflect.DeepEqual(got, tc.want) {
 			t.Errorf("%v gave\n%+v\nwant\n%+v", tc.env, got, tc.want)
@@ -2327,6 +2330,7 @@ func TestLogsEachSettingWithItsValue(t *testing.T) {
 		wafDisabledRules:     defaultWAFDisabledRules,
 		wafExemptPaths:       "",
 		wafBodyLimit:         off,
+		exclusionsFile:       "",
 		trapPaths:            "",
 		errorBurstThreshold:  "30",
 		logRemoteURL:         "",
@@ -4,6 +4,7 @@
 package servewaf

 import (
+	"fmt"
 	"io"
 	"log/slog"
 	"net/http"
@@ -60,6 +61,9 @@ type Params struct {
 	// LookupFile is the lookup database they are looked up in while
 	// SWWAF_LOOKUP_SOURCE is file, and nil otherwise.
 	LookupFile *lookup.File
+	// CoreRuleSet is what NewCoreRuleSet returns: what inspects requests
+	// while SWWAF_WAF_MODE is not off, and nil while it is.
+	CoreRuleSet *waf.CoreRuleSet
 	// Now tells the time by which requests are counted for the rate
 	// limits, bans are made and run out, and GeoJS's answers are kept,
 	// normally time.Now in UTC, the time the state files give.
@@ -144,7 +148,7 @@ func newHandler(params Params) *handler {
 		dnsbl:       dnsbl,
 		abuseIPDB:   abuseIPDB,
 		rules:       params.Rules,
-		coreRuleSet: newCoreRuleSet(params.Config),
+		coreRuleSet: params.CoreRuleSet,
 		alerts:      params.Alerts,
 	}
 	h.geojs = lookup.New(lookup.Params{
@@ -202,29 +206,35 @@ func newReputation(
 	return lists, dnsbl, abuseIPDB
 }

-// newCoreRuleSet returns the Core Rule Set at SWWAF_WAF_PARANOIA_LEVEL,
+// NewCoreRuleSet returns the Core Rule Set at SWWAF_WAF_PARANOIA_LEVEL,
 // without the rules SWWAF_WAF_DISABLED_RULES switches off, reading bodies
-// up to SWWAF_WAF_BODY_LIMIT, or nil while SWWAF_WAF_MODE is off. It reads at
-// most QuestionBodyMaxBytes less one byte: a question's body of
+// up to SWWAF_WAF_BODY_LIMIT, with the exclusions in
+// SWWAF_CORE_RULE_SET_EXCLUSIONS_FILE, or nil while SWWAF_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.
-func newCoreRuleSet(cfg *config.Config) *waf.CoreRuleSet {
-	if cfg.WAFMode == config.WAFModeOff {
-		return nil
+// JSON or XML body over its limit. An exclusions file that cannot be read, does
+// not parse or names an id of smallwebwaf's own rules is an error in every
+// mode. While the mode is off, a set file is loaded with the Core Rule Set only
+// to check it.
+func NewCoreRuleSet(cfg *config.Config) (*waf.CoreRuleSet, error) {
+	if cfg.WAFMode == config.WAFModeOff && cfg.CoreRuleSetExclusionsFile == "" {
+		return nil, nil //nolint:nilnil // off is no Core Rule Set, and no error
 	}

 	coreRuleSet, err := waf.New(waf.Params{
 		ParanoiaLevel: cfg.WAFParanoiaLevel, DisabledRules: cfg.WAFDisabledRules,
-		BodyLimit: min(cfg.WAFBodyLimit, QuestionBodyMaxBytes-1),
+		BodyLimit:      min(cfg.WAFBodyLimit, QuestionBodyMaxBytes-1),
+		ExclusionsFile: cfg.CoreRuleSetExclusionsFile,
 	})
 	if err != nil {
-		// The Core Rule Set is built in, and the settings cannot break it:
-		// the paranoia level is from 1 to 4, and the id of no rule switches
-		// nothing off.
-		panic(err)
+		return nil, fmt.Errorf("SWWAF_CORE_RULE_SET_EXCLUSIONS_FILE: %w", err)
 	}

-	return coreRuleSet
+	if cfg.WAFMode == config.WAFModeOff {
+		return nil, nil //nolint:nilnil // off is no Core Rule Set, and no error
+	}
+
+	return coreRuleSet, nil
 }

 // handler is servewaf's handler. It holds what every request shares; what
@@ -463,6 +463,11 @@ func newServeWAFWith(
 		}
 	}

+	coreRuleSet, err := servewaf.NewCoreRuleSet(cfg)
+	if err != nil {
+		t.Fatalf("Core Rule Set: %v", err)
+	}
+
 	server := build(servewaf.Params{
 		Config:       cfg,
 		RequestLog:   out,
@@ -470,6 +475,7 @@ func newServeWAFWith(
 		GeoJSURL:     geojsURL,
 		AbuseIPDBURL: abuseIPDBURL,
 		LookupFile:   lookupFile,
+		CoreRuleSet:  coreRuleSet,
 		Now:          now,
 		Rules:        ruleFiles,
 		Alerts:       alertQueue,
@@ -29,6 +29,7 @@ import (
 	"sneak.berlin/go/smallwebwaf/internal/rules"
 	"sneak.berlin/go/smallwebwaf/internal/servewaf"
 	"sneak.berlin/go/smallwebwaf/internal/state"
+	"sneak.berlin/go/smallwebwaf/internal/waf"
 )

 // shutdownTimeout is how long requests in progress may take to finish
@@ -150,7 +151,14 @@ func RunServeWAF(ctx context.Context, params Params) int {
 		return 1
 	}

-	server, err := newServer(cfg, stdout, processLog, now, ruleFiles, alertQueue)
+	crs, err := servewaf.NewCoreRuleSet(cfg)
+	if err != nil {
+		processLog.Error("cannot use the Core Rule Set", "error", err.Error())
+
+		return 1
+	}
+
+	server, err := newServer(cfg, stdout, processLog, now, ruleFiles, alertQueue, crs)
 	if err != nil {
 		processLog.Error("cannot use the lookup database", "error", err.Error())

@@ -170,8 +178,7 @@ func RunServeWAF(ctx context.Context, params Params) int {

 	listener, err := (&net.ListenConfig{}).Listen(ctx, "tcp", cfg.ListenAddr)
 	if err != nil {
-		processLog.Error("cannot listen on SWWAF_LISTEN_ADDR",
-			"error", err.Error())
+		processLog.Error("cannot listen on SWWAF_LISTEN_ADDR", "error", err.Error())

 		return 1
 	}
@@ -190,6 +197,7 @@ func RunServeWAF(ctx context.Context, params Params) int {
 func newServer(
 	cfg *config.Config, stdout io.Writer, processLog *slog.Logger,
 	now func() time.Time, ruleFiles *rules.Files, alertQueue *alerts.Queue,
+	crs *waf.CoreRuleSet,
 ) (*servewaf.Server, error) {
 	var lookupFile *lookup.File

@@ -214,6 +222,7 @@ func newServer(
 		GeoJSURL:     lookup.URL,
 		AbuseIPDBURL: reputation.AbuseIPDBURL,
 		LookupFile:   lookupFile,
+		CoreRuleSet:  crs,
 		Now:          now,
 		Rules:        ruleFiles,
 		Alerts:       alertQueue,
@@ -19,6 +19,7 @@ import (
 	"testing"
 	"time"

+	"sneak.berlin/go/smallwebwaf/internal/config"
 	"sneak.berlin/go/smallwebwaf/internal/lookup/lookuptest"
 	"sneak.berlin/go/smallwebwaf/internal/servewaf"
 	"sneak.berlin/go/smallwebwaf/internal/smallwebwaf"
@@ -551,6 +552,56 @@ func TestRulesDirThatDoesNotExistStopsTheStart(t *testing.T) {
 		": no such file or directory")
 }

+func TestCoreRuleSetExclusionsFileThatCannotBeReadStopsTheStart(t *testing.T) {
+	t.Parallel()
+
+	path := filepath.Join(t.TempDir(), "crs-exclusions.conf")
+	out := &output{}
+
+	status := run(t.Context(), map[string]string{
+		listenAddr: localhost + ":0", stateDir: t.TempDir(), rulesDir: t.TempDir(),
+		"SWWAF_CORE_RULE_SET_EXCLUSIONS_FILE": path,
+	}, out)
+	if status != 1 {
+		t.Fatalf("exit status %d, want 1", status)
+	}
+
+	line := out.line(t, "msg", "cannot use the Core Rule Set")
+	want := "SWWAF_CORE_RULE_SET_EXCLUSIONS_FILE: read the exclusions file: open " +
+		path + ": no such file or directory"
+
+	if line["error"] != want {
+		t.Errorf("start refused with %v, want the error %q", line, want)
+	}
+}
+
+func TestCoreRuleSetExclusionsFileThatCannotBeUsedStopsTheStartWhileTheCoreRuleSetIsOff(
+	t *testing.T,
+) {
+	t.Parallel()
+
+	broken := filepath.Join(t.TempDir(), "broken.conf")
+
+	err := os.WriteFile(broken, []byte("SecNoSuchDirective On\n"), 0o600)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	for _, path := range []string{filepath.Join(t.TempDir(), "missing.conf"), broken} {
+		out := &output{}
+
+		status := run(t.Context(), map[string]string{
+			listenAddr: localhost + ":0", stateDir: t.TempDir(), rulesDir: t.TempDir(),
+			"SWWAF_WAF_MODE": config.WAFModeOff, "SWWAF_CORE_RULE_SET_EXCLUSIONS_FILE": path,
+		}, out)
+		if status != 1 {
+			t.Fatalf("%s: exit status %d, want 1", path, status)
+		}
+
+		out.line(t, "msg", "cannot use the Core Rule Set")
+	}
+}
+
 func TestLookupDatabaseReplacedWhileRunningTakesEffect(t *testing.T) {
 	t.Parallel()

@@ -0,0 +1,337 @@
+# Ordinary gitea requests that the Core Rule Set must let through with
+# deploy/gitea/crs-exclusions.conf. Each line is a path and query, and may end
+# with one header after a space. The tests of internal/waf inspect each as a GET,
+# and script/gitea-setup sends each to gitea through the setup as a GET. The Core
+# Rule Set reads the query and the headers the same way for any method.
+
+# Searches with ordinary words and symbols.
+/owner/repo/search?q=package.json
+/owner/repo/search?q=.gitignore
+/owner/repo/search?q=docker-compose.yml
+/owner/repo/search?q=python3
+/owner/repo/search?q=ssh%20key
+/owner/repo/search?q=feat%2Fdocker-support
+/owner/repo/search?q=ls%20-la
+/owner/repo/search?q=sed%20-i
+/owner/repo/search?q=%2Fbin%2Fsh
+/owner/repo/search?q=%60make%20check%60
+/owner/repo/search?q=%60whoami%60
+/owner/repo/search?q=fetch%28
+/owner/repo/search?q=%24%7BVAR%7D
+/owner/repo/search?q=%24%28pwd%29
+/owner/repo/search?q=process.env
+/owner/repo/search?q=%3Cimg%20src%3D
+/owner/repo/search?q=%3Cscript%3E
+/owner/repo/search?q=SELECT%20%2A%20FROM%20users%20WHERE
+/owner/repo/search?q=union%20select
+/owner/repo/search?q=http%3A%2F%2F127.0.0.1%3A8080
+/owner/repo/search?q=..%2F
+/owner/repo/search?q=%2Fetc%2Fpasswd
+/owner/repo/search?q=eval%28
+/owner/repo/search?q=chmod%20%2Bx
+/owner/repo/search?q=echo%20%24PATH
+/owner/repo/search?q=java.lang.Runtime
+/owner/repo/search?q=document.cookie
+/owner/repo/search?q=alert%281%29
+/owner/repo/search?q=__proto__
+/owner/repo/search?q=C%3A%5CWindows%5CSystem32
+/owner/repo/search?q=Invoke-WebRequest
+/owner/repo/search?q=if%20%28a%20%3D%3D%20b%29%20%7B
+/owner/repo/search?q=sudo%20apt%20install
+/owner/repo/search?q=~%2F.ssh%2Fconfig
+/owner/repo/search?q=.htaccess
+/owner/repo/search?q=%24_GET%5B
+/owner/repo/search?q=%24_POST
+/owner/repo/search?q=%24_SERVER%5B%27REQUEST_URI%27%5D
+/owner/repo/search?q=%3C%3Fphp%20echo
+/owner/repo/search?q=information_schema
+/owner/repo/search?q=LIKE%20%27%25foo%25%27
+/owner/repo/search?q=onClick%3D%7B
+/explore/repos?q=SELECT%20%2A%20FROM%20users%20WHERE
+/explore/repos?q=%3Cimg%20src%3D
+/explore/code?q=SELECT%20%2A%20FROM%20users%20WHERE
+/explore/code?q=%3Cimg%20src%3D
+/owner/repo/issues?type=all&state=open&q=SELECT%20%2A%20FROM%20users%20WHERE
+/owner/repo/issues?type=all&state=open&q=%3Cimg%20src%3D
+/owner/repo/pulls?q=SELECT%20%2A%20FROM%20users%20WHERE
+/owner/repo/pulls?q=%3Cimg%20src%3D
+/issues?type=your_repositories&q=SELECT%20%2A%20FROM%20users%20WHERE
+/issues?type=your_repositories&q=%3Cimg%20src%3D
+/owner/repo/commits/branch/main/search?q=SELECT%20%2A%20FROM%20users%20WHERE
+/owner/repo/commits/branch/main/search?q=%3Cimg%20src%3D
+/owner/repo/wiki/search?q=SELECT%20%2A%20FROM%20users%20WHERE
+/owner/repo/wiki/search?q=%3Cimg%20src%3D
+/owner/repo/branches?q=SELECT%20%2A%20FROM%20users%20WHERE
+/owner/repo/branches?q=%3Cimg%20src%3D
+/owner/repo/releases?q=SELECT%20%2A%20FROM%20users%20WHERE
+/owner/repo/releases?q=%3Cimg%20src%3D
+/owner/-/packages?q=SELECT%20%2A%20FROM%20users%20WHERE
+/owner/-/packages?q=%3Cimg%20src%3D
+/user/search?q=SELECT%20%2A%20FROM%20users%20WHERE
+/user/search?q=%3Cimg%20src%3D
+/api/v1/repos/search?q=SELECT%20%2A%20FROM%20users%20WHERE
+/api/v1/repos/search?q=%3Cimg%20src%3D
+/api/v1/repos/issues/search?q=SELECT%20%2A%20FROM%20users%20WHERE
+/api/v1/repos/issues/search?q=%3Cimg%20src%3D
+/api/v1/repos/owner/repo/issues?q=SELECT%20%2A%20FROM%20users%20WHERE
+/api/v1/repos/owner/repo/issues?q=%3Cimg%20src%3D
+
+# Pages, raw files and edit pages of files, and the API's call for their
+# contents.
+/owner/repo/src/branch/main/package.json
+/owner/repo/raw/branch/main/package.json
+/owner/repo/_edit/main/package.json
+/api/v1/repos/owner/repo/contents/package.json
+/owner/repo/src/branch/main/.gitignore
+/owner/repo/raw/branch/main/.gitignore
+/owner/repo/_edit/main/.gitignore
+/api/v1/repos/owner/repo/contents/.gitignore
+/owner/repo/src/branch/main/docker-compose.yml
+/owner/repo/raw/branch/main/docker-compose.yml
+/owner/repo/_edit/main/docker-compose.yml
+/api/v1/repos/owner/repo/contents/docker-compose.yml
+/owner/repo/src/branch/main/Dockerfile
+/owner/repo/raw/branch/main/Dockerfile
+/owner/repo/_edit/main/Dockerfile
+/api/v1/repos/owner/repo/contents/Dockerfile
+/owner/repo/src/branch/main/.htaccess
+/owner/repo/raw/branch/main/.htaccess
+/owner/repo/_edit/main/.htaccess
+/api/v1/repos/owner/repo/contents/.htaccess
+/owner/repo/src/branch/main/rootfs/etc/passwd
+/owner/repo/raw/branch/main/rootfs/etc/passwd
+/owner/repo/_edit/main/rootfs/etc/passwd
+/api/v1/repos/owner/repo/contents/rootfs/etc/passwd
+/owner/repo/src/branch/main/bin/docker-entrypoint
+/owner/repo/raw/branch/main/bin/docker-entrypoint
+/owner/repo/_edit/main/bin/docker-entrypoint
+/api/v1/repos/owner/repo/contents/bin/docker-entrypoint
+/owner/repo/src/branch/main/scripts/python3-setup.sh
+/owner/repo/raw/branch/main/scripts/python3-setup.sh
+/owner/repo/_edit/main/scripts/python3-setup.sh
+/api/v1/repos/owner/repo/contents/scripts/python3-setup.sh
+/owner/repo/src/branch/main/src/java.base/share/classes/java/lang/Runtime.java
+/owner/repo/raw/branch/main/src/java.base/share/classes/java/lang/Runtime.java
+/owner/repo/_edit/main/src/java.base/share/classes/java/lang/Runtime.java
+/api/v1/repos/owner/repo/contents/src/java.base/share/classes/java/lang/Runtime.java
+/owner/repo/src/branch/main/java.lang.String.md
+/owner/repo/raw/branch/main/java.lang.String.md
+/owner/repo/_edit/main/java.lang.String.md
+/api/v1/repos/owner/repo/contents/java.lang.String.md
+/owner/repo/src/branch/main/META-INF/services/org.apache.commons.logging.LogFactory
+/owner/repo/raw/branch/main/META-INF/services/org.apache.commons.logging.LogFactory
+/owner/repo/_edit/main/META-INF/services/org.apache.commons.logging.LogFactory
+/api/v1/repos/owner/repo/contents/META-INF/services/org.apache.commons.logging.LogFactory
+/owner/repo/src/branch/main/process.env.d.ts
+/owner/repo/raw/branch/main/process.env.d.ts
+/owner/repo/_edit/main/process.env.d.ts
+/api/v1/repos/owner/repo/contents/process.env.d.ts
+/owner/repo/src/branch/main/document.write.js
+/owner/repo/raw/branch/main/document.write.js
+/owner/repo/_edit/main/document.write.js
+/api/v1/repos/owner/repo/contents/document.write.js
+/owner/repo/src/branch/main/test/fixtures/__proto__.json
+/owner/repo/raw/branch/main/test/fixtures/__proto__.json
+/owner/repo/_edit/main/test/fixtures/__proto__.json
+/api/v1/repos/owner/repo/contents/test/fixtures/__proto__.json
+/owner/repo/src/branch/main/install-script.sh
+/owner/repo/raw/branch/main/install-script.sh
+/owner/repo/_edit/main/install-script.sh
+/api/v1/repos/owner/repo/contents/install-script.sh
+/owner/repo/src/branch/main/src/backend/catalog/information_schema.sql
+/owner/repo/raw/branch/main/src/backend/catalog/information_schema.sql
+/owner/repo/_edit/main/src/backend/catalog/information_schema.sql
+/api/v1/repos/owner/repo/contents/src/backend/catalog/information_schema.sql
+/owner/repo/src/branch/main/docs/a%20b.xhtml
+/owner/repo/raw/branch/main/docs/a%20b.xhtml
+/owner/repo/_edit/main/docs/a%20b.xhtml
+/api/v1/repos/owner/repo/contents/docs/a%20b.xhtml
+/owner/repo/src/branch/main/%5Bdraft%5D.md
+/owner/repo/raw/branch/main/%5Bdraft%5D.md
+/owner/repo/_edit/main/%5Bdraft%5D.md
+/api/v1/repos/owner/repo/contents/%5Bdraft%5D.md
+/owner/repo/src/branch/main/notes.txt~
+/owner/repo/raw/branch/main/notes.txt~
+/owner/repo/_edit/main/notes.txt~
+/api/v1/repos/owner/repo/contents/notes.txt~
+
+# File names in the query string: the commit graph of a file, the API's lists
+# of its commits and of its contents, an issue opened from a template, and the
+# sign-in page on the way to its edit page.
+/owner/repo/graph?file=package.json
+/api/v1/repos/owner/repo/commits?path=package.json
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22package.json%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Fpackage.json
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Fpackage.json
+/owner/repo/graph?file=.gitignore
+/api/v1/repos/owner/repo/commits?path=.gitignore
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22.gitignore%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2F.gitignore
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2F.gitignore
+/owner/repo/graph?file=docker-compose.yml
+/api/v1/repos/owner/repo/commits?path=docker-compose.yml
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22docker-compose.yml%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Fdocker-compose.yml
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Fdocker-compose.yml
+/owner/repo/graph?file=.htaccess
+/api/v1/repos/owner/repo/commits?path=.htaccess
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22.htaccess%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2F.htaccess
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2F.htaccess
+/owner/repo/graph?file=rootfs%2Fetc%2Fpasswd
+/api/v1/repos/owner/repo/commits?path=rootfs%2Fetc%2Fpasswd
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22rootfs%2Fetc%2Fpasswd%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Frootfs%2Fetc%2Fpasswd
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Frootfs%2Fetc%2Fpasswd
+/owner/repo/graph?file=bin%2Fdocker-entrypoint
+/api/v1/repos/owner/repo/commits?path=bin%2Fdocker-entrypoint
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22bin%2Fdocker-entrypoint%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Fbin%2Fdocker-entrypoint
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Fbin%2Fdocker-entrypoint
+/owner/repo/graph?file=scripts%2Fpython3-setup.sh
+/api/v1/repos/owner/repo/commits?path=scripts%2Fpython3-setup.sh
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22scripts%2Fpython3-setup.sh%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Fscripts%2Fpython3-setup.sh
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Fscripts%2Fpython3-setup.sh
+/owner/repo/graph?file=src%2Fjava.base%2Fshare%2Fclasses%2Fjava%2Flang%2FRuntime.java
+/api/v1/repos/owner/repo/commits?path=src%2Fjava.base%2Fshare%2Fclasses%2Fjava%2Flang%2FRuntime.java
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22src%2Fjava.base%2Fshare%2Fclasses%2Fjava%2Flang%2FRuntime.java%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Fsrc%2Fjava.base%2Fshare%2Fclasses%2Fjava%2Flang%2FRuntime.java
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Fsrc%2Fjava.base%2Fshare%2Fclasses%2Fjava%2Flang%2FRuntime.java
+/owner/repo/graph?file=java.lang.String.md
+/api/v1/repos/owner/repo/commits?path=java.lang.String.md
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22java.lang.String.md%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Fjava.lang.String.md
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Fjava.lang.String.md
+/owner/repo/graph?file=META-INF%2Fservices%2Forg.apache.commons.logging.LogFactory
+/api/v1/repos/owner/repo/commits?path=META-INF%2Fservices%2Forg.apache.commons.logging.LogFactory
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22META-INF%2Fservices%2Forg.apache.commons.logging.LogFactory%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2FMETA-INF%2Fservices%2Forg.apache.commons.logging.LogFactory
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2FMETA-INF%2Fservices%2Forg.apache.commons.logging.LogFactory
+/owner/repo/graph?file=process.env.d.ts
+/api/v1/repos/owner/repo/commits?path=process.env.d.ts
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22process.env.d.ts%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Fprocess.env.d.ts
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Fprocess.env.d.ts
+/owner/repo/graph?file=document.write.js
+/api/v1/repos/owner/repo/commits?path=document.write.js
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22document.write.js%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Fdocument.write.js
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Fdocument.write.js
+/owner/repo/graph?file=test%2Ffixtures%2F__proto__.json
+/api/v1/repos/owner/repo/commits?path=test%2Ffixtures%2F__proto__.json
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22test%2Ffixtures%2F__proto__.json%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Ftest%2Ffixtures%2F__proto__.json
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Ftest%2Ffixtures%2F__proto__.json
+/owner/repo/graph?file=install-script.sh
+/api/v1/repos/owner/repo/commits?path=install-script.sh
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22install-script.sh%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Finstall-script.sh
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Finstall-script.sh
+/owner/repo/graph?file=src%2Fbackend%2Fcatalog%2Finformation_schema.sql
+/api/v1/repos/owner/repo/commits?path=src%2Fbackend%2Fcatalog%2Finformation_schema.sql
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22src%2Fbackend%2Fcatalog%2Finformation_schema.sql%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Fsrc%2Fbackend%2Fcatalog%2Finformation_schema.sql
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Fsrc%2Fbackend%2Fcatalog%2Finformation_schema.sql
+/owner/repo/graph?file=docs%2Fa%20b.xhtml
+/api/v1/repos/owner/repo/commits?path=docs%2Fa%20b.xhtml
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22docs%2Fa%20b.xhtml%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2Fdocs%2Fa%20b.xhtml
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2Fdocs%2Fa%20b.xhtml
+/owner/repo/graph?file=%5Bdraft%5D.md
+/api/v1/repos/owner/repo/commits?path=%5Bdraft%5D.md
+/api/v1/repos/owner/repo/file-contents?body=%7B%22files%22%3A%5B%22%5Bdraft%5D.md%22%5D%7D
+/owner/repo/issues/new?template=.gitea%2FISSUE_TEMPLATE%2F%5Bdraft%5D.md
+/user/login?redirect_to=%2Fowner%2Frepo%2F_edit%2Fmain%2F%5Bdraft%5D.md
+
+# File names of attachments uploaded through the API, to a release, an issue and
+# a comment.
+/api/v1/repos/owner/repo/releases/1/assets?name=package.json
+/api/v1/repos/owner/repo/releases/1/assets?name=.gitignore
+/api/v1/repos/owner/repo/releases/1/assets?name=docker-compose.yml
+/api/v1/repos/owner/repo/releases/1/assets?name=.htaccess
+/api/v1/repos/owner/repo/releases/1/assets?name=docker-entrypoint
+/api/v1/repos/owner/repo/releases/1/assets?name=python3-setup.sh
+/api/v1/repos/owner/repo/releases/1/assets?name=Runtime.java
+/api/v1/repos/owner/repo/releases/1/assets?name=org.apache.commons.logging.LogFactory
+/api/v1/repos/owner/repo/releases/1/assets?name=%5Bdraft%5D.md
+/api/v1/repos/owner/repo/releases/1/assets?name=notes.txt~
+/api/v1/repos/owner/repo/releases/1/assets?name=install-script.sh
+/api/v1/repos/owner/repo/issues/1/assets?name=install-script.sh
+/api/v1/repos/owner/repo/issues/comments/1/assets?name=install-script.sh
+/api/v1/repos/owner/repo/releases/1/assets?name=process.env.d.ts
+/api/v1/repos/owner/repo/issues/1/assets?name=process.env.d.ts
+/api/v1/repos/owner/repo/issues/comments/1/assets?name=process.env.d.ts
+/api/v1/repos/owner/repo/releases/1/assets?name=java.lang.String.md
+/api/v1/repos/owner/repo/issues/1/assets?name=java.lang.String.md
+/api/v1/repos/owner/repo/issues/comments/1/assets?name=java.lang.String.md
+/api/v1/repos/owner/repo/releases/1/assets?name=information_schema.sql
+/api/v1/repos/owner/repo/issues/1/assets?name=information_schema.sql
+/api/v1/repos/owner/repo/issues/comments/1/assets?name=information_schema.sql
+/api/v1/repos/owner/repo/releases/1/assets?name=document.write.js
+/api/v1/repos/owner/repo/issues/1/assets?name=document.write.js
+/api/v1/repos/owner/repo/issues/comments/1/assets?name=document.write.js
+/api/v1/repos/owner/repo/releases/1/assets?name=__proto__.json
+/api/v1/repos/owner/repo/issues/1/assets?name=__proto__.json
+/api/v1/repos/owner/repo/issues/comments/1/assets?name=__proto__.json
+/api/v1/repos/owner/repo/releases/1/assets?name=index.xhtml
+/api/v1/repos/owner/repo/issues/1/assets?name=index.xhtml
+/api/v1/repos/owner/repo/issues/comments/1/assets?name=index.xhtml
+
+# An artifact upload from actions/upload-artifact@v3, which sends Content-Range.
+/api/actions_pipeline/_apis/pipelines/workflows/1/artifacts/9b7c1f3a/upload?itemPath=artifact%2Freport.txt Content-Range: bytes 0-9/10
+
+# Branch and tag names in the query string: deleting a branch, starting a
+# release from a tag, a branch protection rule, a directory listing's last
+# commits, and a container image push that reuses a layer.
+/owner/repo/branches?name=docker-build
+/owner/repo/releases/new?tag=docker-build
+/owner/repo/settings/branches/edit?rule_name=docker-build
+/owner/repo/lastcommit/main/src?refSubUrl=branch%2Fdocker-build
+/v2/owner/app/blobs/uploads/?mount=sha256%3A0000&from=owner%2Fdocker-build
+/owner/repo/branches?name=feat%2Fdocker-support
+/owner/repo/releases/new?tag=feat%2Fdocker-support
+/owner/repo/settings/branches/edit?rule_name=feat%2Fdocker-support
+/owner/repo/lastcommit/main/src?refSubUrl=branch%2Ffeat%2Fdocker-support
+/v2/owner/app/blobs/uploads/?mount=sha256%3A0000&from=owner%2Ffeat%2Fdocker-support
+/owner/repo/branches?name=renovate%2Fdocker-build-push-action-6.x
+/owner/repo/releases/new?tag=renovate%2Fdocker-build-push-action-6.x
+/owner/repo/settings/branches/edit?rule_name=renovate%2Fdocker-build-push-action-6.x
+/owner/repo/lastcommit/main/src?refSubUrl=branch%2Frenovate%2Fdocker-build-push-action-6.x
+/v2/owner/app/blobs/uploads/?mount=sha256%3A0000&from=owner%2Frenovate%2Fdocker-build-push-action-6.x
+/owner/repo/branches?name=python3-migration
+/owner/repo/releases/new?tag=python3-migration
+/owner/repo/settings/branches/edit?rule_name=python3-migration
+/owner/repo/lastcommit/main/src?refSubUrl=branch%2Fpython3-migration
+/v2/owner/app/blobs/uploads/?mount=sha256%3A0000&from=owner%2Fpython3-migration
+/owner/repo/branches?name=ansible-roles
+/owner/repo/releases/new?tag=ansible-roles
+/owner/repo/settings/branches/edit?rule_name=ansible-roles
+/owner/repo/lastcommit/main/src?refSubUrl=branch%2Fansible-roles
+/v2/owner/app/blobs/uploads/?mount=sha256%3A0000&from=owner%2Fansible-roles
+/owner/repo/branches?name=whoami
+/owner/repo/releases/new?tag=whoami
+/owner/repo/settings/branches/edit?rule_name=whoami
+/owner/repo/lastcommit/main/src?refSubUrl=branch%2Fwhoami
+/v2/owner/app/blobs/uploads/?mount=sha256%3A0000&from=owner%2Fwhoami
+
+# Pages a signed-in user opens.
+/
+/owner/repo
+/owner/repo/issues
+/owner/repo/pulls
+/owner/repo/releases
+/owner/repo/wiki
+/owner/repo/activity
+/owner/repo/branches
+/owner/repo/tags
+/owner/repo/settings
+/owner/repo/actions
+/owner/repo/compare/main...main
+/owner/repo/commits/branch/main
+/owner/repo/archive/main.zip
+/notifications
+/user/settings
+/user/settings/applications
+/explore/repos
+/-/admin
@@ -1,8 +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 SWWAF_WAF_BODY_LIMIT is set, with the six changes smallwebwaf
-// makes to it, as "Attack detection" under "Settings" in SPEC.md describes
-// them. It reads no response.
+// body while SWWAF_WAF_BODY_LIMIT is set, with the seven changes smallwebwaf
+// makes to it and the exclusions in SWWAF_CORE_RULE_SET_EXCLUSIONS_FILE, as
+// "Attack detection" under "Settings" in SPEC.md describes them. It reads no
+// response.
 //
 // smallwebwaf 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
@@ -11,10 +12,13 @@
 package waf

 import (
+	"errors"
 	"fmt"
 	"io"
 	"net/http"
 	"net/netip"
+	"os"
+	"regexp"
 	"slices"
 	"strconv"
 	"strings"
@@ -26,12 +30,13 @@ import (
 )

 // directives are the Core Rule Set as smallwebwaf runs it, with the
-// paranoia level for %d, and bodyDirectives for %s while
-// SWWAF_WAF_BODY_LIMIT is set. Each rule smallwebwaf adds has an id from
-// 900000 to 900999, the ids the Core Rule Set keeps for the rules that set
-// it up, which SWWAF_WAF_DISABLED_RULES refuses, so that no setting
-// switches one off. Coraza joins a line ending in \ to the next, without
-// the spaces at the start of the next.
+// paranoia level for %d, bodyDirectives for the first %s while
+// SWWAF_WAF_BODY_LIMIT is set, and the exclusions file for the second.
+// Each rule smallwebwaf adds has an id from 900000 to 900999, the ids the
+// Core Rule Set keeps for the rules that set it up, which
+// SWWAF_WAF_DISABLED_RULES and the exclusions file refuse, so that no
+// setting switches one off. Coraza joins a line ending in \ to the next,
+// without the spaces at the start of the next.
 const directives = `
 # The engine only detects. smallwebwaf compares the request's anomaly
 # score with SWWAF_WAF_ANOMALY_THRESHOLD itself, in block and detect mode
@@ -69,6 +74,11 @@ SecArgumentsLimit 1000
 SecRule ARGUMENTS_LIMIT_REACHED "@eq 1" "id:900300,phase:2,pass,\
    severity:'CRITICAL',setvar:'tx.inbound_anomaly_score_pl1=+5'"

+# The exclusions file comes before the rules, where the Core Rule Set puts
+# its own file of exclusions that run before the rules, so that they run
+# before the rules of phase 1 too.
+%s
+
 # The sixth: only the rules for requests are loaded, and no response is
 # inspected.
 Include @owasp_crs/REQUEST-*.conf
@@ -100,6 +110,13 @@ SecRuleUpdateTargetById 932260 "!ARGS:path|!ARGS:files|!ARGS:skip-to|\
 # Inspect.
 SecRuleUpdateTargetById 932340 "!REQUEST_HEADERS:Referer"
 SecRuleUpdateTargetById 944110 "!REQUEST_HEADERS:Referer"
+
+# The seventh: 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.
+SecRule REQUEST_FILENAME "@rx ^/v2/.+/blobs/uploads/$" \
+    "id:900500,phase:1,pass,nolog,ctl:ruleRemoveTargetById=932260;ARGS:from"
 `

 // bodyDirectives have the Core Rule Set read the part of a request body
@@ -160,6 +177,51 @@ type Params struct {
 	// BodyLimit is the most of a request body the Core Rule Set reads
 	// (SWWAF_WAF_BODY_LIMIT), 0 while it is off and it reads none.
 	BodyLimit int64
+	// ExclusionsFile is the path of a file of exclusions loaded before the
+	// Core Rule Set's rules (SWWAF_CORE_RULE_SET_EXCLUSIONS_FILE), "" while
+	// there is none.
+	ExclusionsFile string
+}
+
+// The ids of smallwebwaf's own rules, which an exclusions file may not
+// name.
+const (
+	firstOwnRuleID = 900000
+	lastOwnRuleID  = 900999
+)
+
+// numberOrRange matches a number, or a range of numbers such as
+// 900000-900999.
+var numberOrRange = regexp.MustCompile(`(\d+)(?:-(\d+))?`)
+
+// errSmallwebwafRuleID is the error of an exclusions file that names an
+// id of smallwebwaf's own rules.
+var errSmallwebwafRuleID = errors.New("an id of smallwebwaf's own rules")
+
+// ownRuleNamed returns the first number or range in exclusions, the text
+// of an exclusions file, that takes in an id of smallwebwaf's own rules,
+// or "" if none does. Comment lines are skipped, as Coraza skips them.
+func ownRuleNamed(exclusions string) string {
+	for line := range strings.Lines(exclusions) {
+		if strings.HasPrefix(strings.TrimSpace(line), "#") {
+			continue
+		}
+
+		for _, match := range numberOrRange.FindAllStringSubmatch(line, -1) {
+			first, _ := strconv.Atoi(match[1])
+
+			last := first
+			if match[2] != "" {
+				last, _ = strconv.Atoi(match[2])
+			}
+
+			if first <= lastOwnRuleID && last >= firstOwnRuleID {
+				return match[0]
+			}
+		}
+	}
+
+	return ""
 }

 // CoreRuleSet is the Core Rule Set, ready to inspect requests. It is safe
@@ -169,16 +231,35 @@ type CoreRuleSet struct {
 	bodyLimit int64
 }

-// New returns the Core Rule Set with the six changes, at params'
-// paranoia level, without the rules it switches off, and reading request
-// bodies up to params' limit.
+// New returns the Core Rule Set with the seven 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 that cannot be
+// read, does not parse or names an id of smallwebwaf's own rules is an
+// error.
 func New(params Params) (*CoreRuleSet, error) {
 	body := ""
 	if params.BodyLimit > 0 {
 		body = fmt.Sprintf(bodyDirectives, params.BodyLimit)
 	}

-	text := fmt.Sprintf(directives, params.ParanoiaLevel, body)
+	exclusions := ""
+
+	if params.ExclusionsFile != "" {
+		file, err := os.ReadFile(params.ExclusionsFile)
+		if err != nil {
+			return nil, fmt.Errorf("read the exclusions file: %w", err)
+		}
+
+		exclusions = string(file)
+
+		if named := ownRuleNamed(exclusions); named != "" {
+			return nil, fmt.Errorf("the exclusions file names %s: %w", named,
+				errSmallwebwafRuleID)
+		}
+	}
+
+	text := fmt.Sprintf(directives, params.ParanoiaLevel, body, exclusions)

 	if len(params.DisabledRules) > 0 {
 		ids := make([]string, len(params.DisabledRules))
@@ -5,6 +5,7 @@ import (
 	"net/http/httptest"
 	"net/netip"
 	"net/url"
+	"os"
 	"path/filepath"
 	"reflect"
 	"strconv"
@@ -119,7 +120,7 @@ func atDefaults(t *testing.T) *waf.CoreRuleSet {
 }

 // wantChange checks that crs lets through passes, a gitea request one of
-// the six changes is for, and still finds result in refused, a request
+// the seven changes is for, and still finds result in refused, a request
 // like it that the change is not for.
 func wantChange(
 	t *testing.T, crs *waf.CoreRuleSet, passes, refused request, result waf.Result,
@@ -362,6 +363,167 @@ func TestEachDisabledRuleIsSwitchedOff(t *testing.T) {
 	wantResult(t, newCoreRuleSet(t, 1, 920350, 911100), r, waf.Result{})
 }

+func TestImagePushThatReusesALayerIsNotCheckedForCommandNames(t *testing.T) {
+	t.Parallel()
+
+	crs := atDefaults(t)
+	reuse := "?mount=sha256:0000&from=owner/python3-app"
+
+	wantChange(t, crs, get("/v2/owner/app/blobs/uploads/"+reuse), get("/upload/"+reuse),
+		matched(932260))
+
+	// A command after the image's name is still refused.
+	wantResult(t, crs,
+		get("/v2/owner/app/blobs/uploads/?from=owner/app;cat%20/etc/passwd"),
+		matched(930120, 932160))
+}
+
+// withExclusions returns the Core Rule Set at the defaults, with the
+// exclusions file at path.
+func withExclusions(path string) (*waf.CoreRuleSet, error) {
+	return waf.New(waf.Params{
+		ParanoiaLevel: 1, DisabledRules: defaultDisabledRules, ExclusionsFile: path,
+	})
+}
+
+// exclusionsFile writes text to a file of exclusions and returns its path.
+func exclusionsFile(t *testing.T, text string) string {
+	t.Helper()
+
+	path := filepath.Join(t.TempDir(), "exclusions.conf")
+
+	err := os.WriteFile(path, []byte(text), 0o600)
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	return path
+}
+
+// backupFileExclusion is an exclusions file that switches 920500, a rule
+// of phase 1, off for the path of a backup file under /files/.
+const backupFileExclusion = `SecRule REQUEST_FILENAME "@beginsWith /files/" ` +
+	`"id:1,phase:1,pass,nolog,ctl:ruleRemoveTargetById=920500;REQUEST_FILENAME"` + "\n"
+
+func TestExclusionsFileIsLoadedBeforeTheRules(t *testing.T) {
+	t.Parallel()
+
+	crs, err := withExclusions(exclusionsFile(t, backupFileExclusion))
+	if err != nil {
+		t.Fatalf("load the exclusions: %v", err)
+	}
+
+	wantChange(t, crs, get("/files/notes.txt~"), get("/notes.txt~"), matched(920500))
+}
+
+func TestRuleSwitchedOffAndNamedInTheExclusionsFileIsOff(t *testing.T) {
+	t.Parallel()
+
+	crs, err := waf.New(waf.Params{
+		ParanoiaLevel: 1, DisabledRules: []int{920500},
+		ExclusionsFile: exclusionsFile(t, backupFileExclusion),
+	})
+	if err != nil {
+		t.Fatalf("load the exclusions: %v", err)
+	}
+
+	wantResult(t, crs, get("/notes.txt~"), waf.Result{})
+}
+
+func TestExclusionsFileMayNameAnyNumberInAComment(t *testing.T) {
+	t.Parallel()
+
+	_, err := withExclusions(exclusionsFile(t,
+		"# 942100: GET /issues/900123\n"+backupFileExclusion))
+	if err != nil {
+		t.Errorf("the exclusions did not load: %v", err)
+	}
+}
+
+func TestExclusionsFileThatCannotBeUsedIsAnError(t *testing.T) {
+	t.Parallel()
+
+	for _, path := range []string{
+		filepath.Join(t.TempDir(), "missing.conf"),
+		exclusionsFile(t, "SecNoSuchDirective On\n"),
+		// The Core Rule Set's rules are not loaded yet.
+		exclusionsFile(t, "SecRuleUpdateTargetById 942100 \"!ARGS:id\"\n"),
+		// smallwebwaf's own rules may not be switched off or changed, by
+		// id or in a range.
+		exclusionsFile(t, "SecRuleRemoveById 900300\n"),
+		exclusionsFile(t, "SecRuleRemoveById 899999-901000\n"),
+		exclusionsFile(t, "SecAction \"id:1,phase:1,pass,nolog,"+
+			"ctl:ruleRemoveById=899999-901000\"\n"),
+		exclusionsFile(t, "SecAction \"id:1,phase:1,pass,nolog,"+
+			"ctl:ruleRemoveTargetById=900500;ARGS:from\"\n"),
+	} {
+		_, err := withExclusions(path)
+		if err == nil {
+			t.Errorf("%s loaded", path)
+		}
+	}
+}
+
+// giteaRequests returns the recorded ordinary gitea requests in testdata,
+// which script/gitea-setup sends too. Each has the Referer of a page that
+// names the same, as a page opened from it has.
+func giteaRequests(t *testing.T) []request {
+	t.Helper()
+
+	text, err := os.ReadFile(filepath.Join("testdata", "gitea-requests.txt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	var requests []request
+
+	for line := range strings.Lines(string(text)) {
+		line = strings.TrimSpace(line)
+		if line == "" || strings.HasPrefix(line, "#") {
+			continue
+		}
+
+		target, header, _ := strings.Cut(line, " ")
+
+		headers := []string{"Referer: http://git.example" + target}
+		if header != "" {
+			headers = append(headers, header)
+		}
+
+		requests = append(requests, get(target, headers...))
+	}
+
+	return requests
+}
+
+func TestGiteaExclusionsLetOrdinaryGiteaRequestsThroughAndRefuseAttacks(t *testing.T) {
+	t.Parallel()
+
+	crs, err := withExclusions(filepath.Join("..", "..", "deploy", "gitea",
+		"crs-exclusions.conf"))
+	if err != nil {
+		t.Fatalf("load gitea's exclusions: %v", err)
+	}
+
+	const threshold = 5 // SWWAF_WAF_ANOMALY_THRESHOLD's default
+
+	for _, r := range giteaRequests(t) {
+		if got := inspect(t, crs, r); got.Score >= threshold {
+			t.Errorf("%s %q refused: %+v", r.target, r.headers[1:], got)
+		}
+	}
+
+	for _, attack := range []string{
+		"/owner/repo?id=1'%20OR%20'1'='1",
+		"/owner/repo?id=..%2Fcustom%2Fconf%2Fapp.ini",
+		"/owner/repo?id=%3Cscript%3Ealert(1)%3C%2Fscript%3E",
+	} {
+		if got := inspect(t, crs, get(attack)); got.Score < threshold {
+			t.Errorf("%s let through: %+v", attack, got)
+		}
+	}
+}
+
 // bodyLimit is SWWAF_WAF_BODY_LIMIT in the tests that read bodies.
 const bodyLimit = 8 << 10