Refuse an image URL whose source path or query holds a # (closes #286)

A # written as %23 in the source path or query reached the parser
decoded and stayed in the source URL, where Go reads it as the start of
a fragment and drops it before fetching. So each text after the # was
another unsigned spelling of one upstream request, cached under its own
keys. An image URL whose decoded source path or query holds a # is now
refused with 400, signed or not, and README.md's rule for writing a
source path and query says a # cannot be part of either.

Model: opus-5-5

README.md

@@ -323,8 +323,9 @@ first `/`, the size and format after the last `/`, and between them the source
 path up to the first `?` and the source query after it. So the `?` before the
 query, any `?` in the query, and every `%` in the source path or query must be
 percent-encoded, as `%3F` and `%25`. Any other character may be written as
-itself or percent-encoded: `/`, `;`, `,`, `=` and `&` work either way. For
-example,
+itself or percent-encoded: `/`, `;`, `,`, `=` and `&` work either way. Neither
+the source path nor the source query may hold a `#`, and an image URL that
+writes one as `%23` is refused with 400. For example,
 `https://cdn.example.com/img?url=https://origin.example.com/my%20cat.jpg` at
 800x600 WebP is
 `/v1/image/cdn.example.com/img%3Furl=https://origin.example.com/my%2520cat.jpg/800x600.webp`,

TODO.md

@@ -30,6 +30,11 @@ P2: security: per-origin rate limiting
 
 # Completed Steps
 
+- 2026-10-15 a `/v1/image/` URL whose source path or source query holds a `#`,
+  written as `%23`, is refused with 400 (closes #286): the source URL built from
+  it ended at the `#` when fetched, so each text after it fetched the same
+  upstream image, without a signature for an allowlisted host, and cached it
+  under keys of its own. `README.md` says neither may hold a `#`.
 - 2026-10-15 the host of a `/v1/image/` URL must be a host name or an IPv4
   address (letters, digits, hyphens, underscores and dots) or an IPv6 address in
   brackets, either one optionally followed by `:` and a port, and any other host

internal/handlers/image_errors_internal_test.go

@@ -340,3 +340,51 @@ func TestHandleImage_HostForms_Served(t *testing.T) {
 		})
 	}
 }
+
+// TestHandleImage_HashInSourcePathOrQuery_Returns400 sends image URLs whose
+// source path or source query holds a "#", written as %23, and checks that
+// each is refused with 400, the one signed for that source path included. The
+// source URL would otherwise end at the "#" when it is fetched, so each text
+// after it would fetch the image at photoPath and cache it under keys of its
+// own.
+func TestHandleImage_HashInSourcePathOrQuery_Returns400(t *testing.T) {
+	t.Parallel()
+
+	photos := newPhotoFetcher(t, allowlistedHost, signedHost)
+	exp := time.Now().Add(time.Hour)
+
+	sig := signature.New(testSigningKey).Sign(&signature.Request{
+		SourceHost: signedHost,
+		SourcePath: photoPath + "#x",
+		Width:      50,
+		Height:     50,
+		Format:     string(imgcache.FormatJPEG),
+		Quality:    85,
+		FitMode:    string(imgcache.FitCover),
+		Expires:    exp,
+	})
+
+	tests := []struct {
+		name   string
+		target string
+	}{
+		{"# in the source path",
+			"/v1/image/" + allowlistedHost + photoPath + "%23x/50x50.jpeg"},
+		{"# in the source query",
+			"/v1/image/" + allowlistedHost + photoPath + "%3Fv=1%23x/50x50.jpeg"},
+		{"# in the source path, signed",
+			fmt.Sprintf("/v1/image/%s%s%%23x/50x50.jpeg?sig=%s&exp=%d",
+				signedHost, photoPath, sig, exp.Unix())},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+
+			rec := sendGet(t, newImageRoute(t, photos), tt.target)
+			checkErrorBody(t, rec, http.StatusBadRequest,
+				`invalid image URL: invalid image path: `+
+					`the source path or query holds a "#"`)
+		})
+	}
+}

internal/imgcache/urlparser.go

@@ -171,6 +171,14 @@ func parseImageComponents(remainder string) (*ParsedURL, error) {
 	// host
 	host = strings.ToLower(host)
 
+	// Go's URL parser, which the fetcher uses, reads a "#" as the start of a
+	// fragment and drops the rest, so each text after it would be another
+	// spelling, cached under its own keys, of one upstream request
+	if strings.Contains(path, "#") {
+		return nil, fmt.Errorf(
+			`%w: the source path or query holds a "#"`, ErrInvalidPath)
+	}
+
 	// Extract query string if present in path
 	if qIndex := strings.Index(path, "?"); qIndex != -1 {
 		query = path[qIndex+1:]