backend/AGENTS.md

@@ -168,11 +168,11 @@ Guidance for OpenCode (and Claude Code) working under `backend/`. See root `AGEN
   served by the one public `GET /covers/{addr}` route from content-addressed
   bytes. There is no proxy, no per-Site rewrite, no second place that decides
   a Cover's renderable address: the wire `cover` is it. The only place a Site
-  name still appears in cover code is the acquisition module, where kagane's
-  image URLs are claimed by `latest.BrowserFetcher` (`browserCoverURL`) because
-  they answer a plain fetch with a challenge and
-  `cross-origin-resource-policy: same-origin`; every other Site's CDN answers
-  plain TLS. Templates render `.Cover` — the wire value — never anything else.
+  name still appears in cover code is the extraction module (`latest`), where
+  kagane's image URLs are claimed by `browserOnlyCoverURL` — they answer a
+  plain fetch with a challenge and `cross-origin-resource-policy: same-origin`;
+  every other Site's CDN answers plain TLS. Templates render `.Cover` — the
+  wire value — never anything else.
 - **Web UI also owns:** session-gated `GET /install/{manga,novel}-bookmark.user.js`
   (renders the bindmounted script with the acting Reader's derived credential
   substituted in — the credential never appears in page markup, the address

backend/cover_test.go

@@ -1,6 +1,7 @@
 package main
 
 import (
+	"database/sql"
 	"net/http"
 	"net/http/httptest"
 	"strings"
@@ -72,18 +73,34 @@ func TestPublicCoverRejectsUnknownAddress(t *testing.T) {
 
 // A content type outside the image set is never echoed back. The old kagane
 // proxy could fetch text/html from a challenged fetch and had to refuse it;
-// the general route's only input is what the store accepted, and the store
-// refuses to record anything that is not an image, so the address that would
-// name one is a miss, not a served body.
+// the general route's only input is the store, and the store refuses to
+// record anything that is not an image — but the guarantee is pinned at the
+// serving boundary, not the write gate, so a poisoned row (migrated data, a
+// writer that skips the gate) is also never served.
 func TestPublicCoverNeverEchoesNonImage(t *testing.T) {
 	const sourceURL = "https://cdn.example/cover"
-	srv, st := newWebTestServer(t, testConfig())
+	st, dsn := newTestStoreURL(t)
+	// The write gate refuses non-image content types outright.
 	if err := st.PutCover(sourceURL, []byte("<script>"), "text/html"); err == nil {
 		t.Fatal("PutCover accepted a non-image content type")
 	}
-	rr := getCover(t, srv, "/covers/"+store.CoverAddress(sourceURL), nil)
+	// A legitimate row, then the content type flipped behind the store's back:
+	// the bytes exist at the address, so only the type is hostile.
+	address := store.CoverAddress(sourceURL)
+	if err := st.SetSeriesCover("asura", "solo", sourceURL, []byte("<script>"), "image/png"); err != nil {
+		t.Fatalf("seed row: %v", err)
+	}
+	db, err := sql.Open("pgx", dsn)
+	if err != nil {
+		t.Fatalf("open %s: %v", dsn, err)
+	}
+	defer db.Close()
+	if _, err := db.Exec(`UPDATE covers SET content_type = 'text/html' WHERE address = $1`, address); err != nil {
+		t.Fatalf("poison row: %v", err)
+	}
+	rr := getCover(t, newRouter(st, testConfig()), "/covers/"+address, nil)
 	if rr.Code == http.StatusOK {
-		t.Fatalf("status = 200, want nothing served for a cover the store refused")
+		t.Fatalf("status = 200, want a refusal for a non-image row (body %q)", rr.Body.String())
 	}
 }
 

backend/internal/api/handlers.go

@@ -150,6 +150,14 @@ func (h *Handler) Cover(w http.ResponseWriter, r *http.Request) {
 		http.NotFound(w, r)
 		return
 	}
+	// Refuse anything the write gate would not have recorded: a poisoned row
+	// (migrated data, a writer that skips the gate) must never be echoed back
+	// as bytes of a type no Cover may have.
+	if _, ok := store.CoverContentType(contentType); !ok {
+		log.Printf("cover %s: refusing non-image content type %q", r.PathValue("address"), contentType)
+		http.NotFound(w, r)
+		return
+	}
 	w.Header().Set("Content-Type", contentType)
 	// Content-addressed, so the bytes at this URL can never change. Public
 	// rather than private: no credential gates the route.

backend/internal/latest/browser.go

@@ -24,26 +24,6 @@ const challengeTimeout = 45 * time.Second
 
 var kaganeSeriesRe = regexp.MustCompile(`^/series/([0-9a-f-]{36})/?$`)
 
-// kaganeImageIDRe pins the only image id the kagane extractor accepts. It
-// arrives from the browser-fetched API body, so it is matched rather than
-// trusted.
-var kaganeImageIDRe = regexp.MustCompile(`^[0-9a-f-]{36}$`)
-
-// kaganeImageURLRe matches the only cover URL Image fetches: the canonical
-// compressed image route kagane's API publishes. It doubles as the byte-fetch
-// router's claim check (fetchCoverBytes) — an address of this shape answers a
-// plain fetch with a challenge, so the browser is the only route for it.
-var kaganeImageURLRe = regexp.MustCompile(`^https://kagane\.to/api/v2/image/([0-9a-f-]{36})/compressed$`)
-
-// browserCoverURL reports whether the browser sidecar is the only fetcher for
-// cover bytes at imageURL. kagane serves them behind the same challenge as its
-// pages, so a plain TLS fetch would only ever retrieve a challenge page and
-// must not be attempted (ADR-0007). Per-Site knowledge, kept in the browser
-// module with the rest of it.
-func browserCoverURL(imageURL string) bool {
-	return kaganeImageURLRe.MatchString(imageURL)
-}
-
 // BrowserFetcher retrieves pages through a remote headless Chrome over the
 // DevTools Protocol.
 //

backend/internal/latest/cover.go

@@ -30,7 +30,7 @@ type CoverBytesFetcher interface {
 // fallback onto a path that cannot succeed. One routing rule for the poll and
 // the acquirer, so the two cannot drift apart.
 func fetchCoverBytes(ctx context.Context, cover string, browser BrowserCoverFetcher, tls CoverBytesFetcher) ([]byte, string, error) {
-	if browserCoverURL(cover) {
+	if browserOnlyCoverURL(cover) {
 		if browser == nil {
 			return nil, "", errors.New("no cover fetcher")
 		}

backend/internal/latest/sites.go

@@ -165,6 +165,23 @@ var singleQuotedMetaAttrRe = regexp.MustCompile(`(?is)([a-z][a-z0-9:_-]*)\s*=\s*
 // the target detail entry avoids matching posters from recommended results.
 var comixInitialDataRe = regexp.MustCompile(`(?is)<script\b[^>]*\bid\s*=\s*["']initial-data["'][^>]*>(.*?)</script>`)
 
+// kaganeImageURLRe matches the canonical compressed image route kagane's API
+// publishes — the only cover URL form the extractor emits and the browser
+// fetcher accepts. The URL is matched in full (scheme, host, id shape) rather
+// than trusted: the value a fetcher is pointed at may have been client-
+// supplied, and a headless browser is a strong SSRF primitive.
+var kaganeImageURLRe = regexp.MustCompile(`^https://kagane\.to/api/v2/image/([0-9a-f-]{36})/compressed$`)
+
+// browserOnlyCoverURL reports whether the browser sidecar is the only fetcher
+// for cover bytes at imageURL. kagane's image route answers a plain fetch with
+// a challenge and `cross-origin-resource-policy: same-origin`, so a TLS fetch
+// would only ever retrieve a challenge page and must not be attempted
+// (ADR-0007). This is the byte-fetch router's per-Site knowledge; it lives in
+// the extraction module, which owns kagane's URL shapes.
+func browserOnlyCoverURL(imageURL string) bool {
+	return kaganeImageURLRe.MatchString(imageURL)
+}
+
 // kagane's browser-fetched series response publishes cover image IDs under
 // series_covers. The API's canonical compressed image route is the only URL
 // form accepted by the store and browser fetcher; no rendition is guessed.
@@ -178,8 +195,12 @@ func kaganeCoverURL(body string) string {
 		return ""
 	}
 	for _, cover := range response.SeriesCovers {
-		if kaganeImageIDRe.MatchString(cover.ImageID) {
-			return "https://kagane.to/api/v2/image/" + cover.ImageID + "/compressed"
+		// Validate the assembled URL against the same regex the browser
+		// fetcher enforces, so the extractor can never emit an address the
+		// fetch would refuse.
+		imageURL := "https://kagane.to/api/v2/image/" + cover.ImageID + "/compressed"
+		if kaganeImageURLRe.MatchString(imageURL) {
+			return imageURL
 		}
 	}
 	return ""