fix(classes): sanitize content_html with bluemonday instead of regex checks

- FormatHTML sanitizes the goldmark output with a bluemonday UGC policy
  extended only with what goldmark and the imported posts and categories
  use; unsafe markup is stripped, as Winter's Html::clean strips it
- HTML the policy keeps whole is stored byte for byte (token comparison)
- CheckHTML keeps its signature and 422 contract, refusing HTML the
  policy would change
- the three regexes are gone: the CR-01 bypasses are neutralized and
  "Data:" or "metadata:" text is no longer refused (WR-01)
This commit is contained in:
2026-10-09 23:35:23 +02:00
parent 03907ee387
commit a3551f2bdf
7 changed files with 367 additions and 73 deletions

View File

@@ -151,3 +151,44 @@ func TestPostsAdminResaveKeepsHTML(t *testing.T) {
env.expect(t, http.StatusOK, http.MethodPut, adminAPI(fmt.Sprintf("%s/%d", adminPostsPath, created.ID)), token, body)
assertHTML("re-save")
}
// TestPostsAdminSaveSanitizesHTML pins CR-01 and WR-01 on the admin write
// path: unsafe markup in content is stripped from content_html, as Winter's
// Html::clean strips it, instead of refusing the save, and a "Data:" label is
// ordinary text. content itself is stored as submitted.
func TestPostsAdminSaveSanitizesHTML(t *testing.T) {
env := newPostsEnv(t)
token := env.admin(t,
controllers.PermissionAccessPosts,
controllers.PermissionAccessPublish,
controllers.PermissionAccessOtherPosts,
)
const content = "<p>Data: 12 maja 2024</p>\n" +
"<p><img src=\"https://cdn.example.test/a.jpg\" alt=\"a\"onerror=\"alert(1)\"></p>\n" +
"<p><a href=\"javascript&#58;alert(1)\">x</a></p>\n" +
"<base href=\"https://evil.test/\">"
rec := env.expect(t, http.StatusCreated, http.MethodPost, adminAPI(adminPostsPath), token, map[string]any{
"title": map[string]any{"en": "Sanitized", "pl": "Oczyszczony"},
"slug": map[string]any{"en": "sanitized-html", "pl": "oczyszczony-html"},
"content": map[string]any{"en": content, "pl": content},
})
var created struct {
ID uint `json:"id"`
}
if err := json.Unmarshal(adminDecode(t, rec).Data, &created); err != nil || created.ID == 0 {
t.Fatalf("create data %s: %v", rec.Body.String(), err)
}
var stored models.Post
if err := env.gdb.First(&stored, created.ID).Error; err != nil {
t.Fatal(err)
}
const want = "<p>Data: 12 maja 2024</p>\n" +
"<p><img src=\"https://cdn.example.test/a.jpg\" alt=\"a\"></p>\n" +
"<p>x</p>"
if got := strings.TrimSpace(stored.ContentHTML); got != want {
t.Fatalf("content_html = %q, want %q", got, want)
}
if stored.Content != content {
t.Fatalf("content = %q, want it stored as submitted", stored.Content)
}
}