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, covers Gitea's search, file-name
  and branch-name fields, Referer, and file paths;
- 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. 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

internal/waf/waf_test.go

@@ -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 +363,126 @@ 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
+}
+
+func TestExclusionsFileIsLoadedAfterTheCoreRuleSet(t *testing.T) {
+	t.Parallel()
+
+	crs, err := withExclusions(exclusionsFile(t,
+		"SecRuleUpdateTargetById 942100 \"!ARGS:id\"\n"))
+	if err != nil {
+		t.Fatalf("load the exclusions: %v", err)
+	}
+
+	wantChange(t, crs, get("/?id=1'%20OR%20'1'='1"), get("/?q=1'%20OR%20'1'='1"),
+		matched(942100))
+}
+
+func TestExclusionsFileThatCannotBeUsedIsAnError(t *testing.T) {
+	t.Parallel()
+
+	for _, path := range []string{
+		filepath.Join(t.TempDir(), "missing.conf"),
+		exclusionsFile(t, "SecNoSuchDirective On\n"),
+		// smallwebwaf's own rules may not be switched off or changed.
+		exclusionsFile(t, "SecRuleRemoveById 900300\n"),
+		exclusionsFile(t, "SecRuleUpdateTargetById 900500 \"!ARGS:x\"\n"),
+	} {
+		_, err := withExclusions(path)
+		if err == nil {
+			t.Errorf("%s loaded", path)
+		}
+	}
+}
+
+// giteaRequests returns the targets of the recorded ordinary gitea requests
+// in testdata, which script/gitea-setup sends too.
+func giteaRequests(t *testing.T) []string {
+	t.Helper()
+
+	text, err := os.ReadFile(filepath.Join("testdata", "gitea-requests.txt"))
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	var targets []string
+
+	for line := range strings.Lines(string(text)) {
+		line = strings.TrimSpace(line)
+		if line != "" && !strings.HasPrefix(line, "#") {
+			targets = append(targets, line)
+		}
+	}
+
+	return targets
+}
+
+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
+
+	// Each with the Referer of a page that names the same, as a page
+	// opened from it has.
+	for _, target := range giteaRequests(t) {
+		r := get(target, "Referer: http://git.example"+target)
+		if got := inspect(t, crs, r); got.Score >= threshold {
+			t.Errorf("%s refused: %+v", target, 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