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

5
go.mod
View File

@@ -8,10 +8,12 @@ require (
git.golem15.com/golem15/summercms v0.1.16
github.com/go-gormigrate/gormigrate/v2 v2.1.7
github.com/jackc/pgx/v5 v5.10.0
github.com/microcosm-cc/bluemonday v1.0.27
github.com/testcontainers/testcontainers-go v0.44.0
github.com/testcontainers/testcontainers-go/modules/postgres v0.44.0
github.com/yuin/goldmark v1.8.6
gocloud.dev v0.46.0
golang.org/x/net v0.58.0
gorm.io/gorm v1.31.2
)
@@ -19,6 +21,7 @@ require (
dario.cat/mergo v1.0.2 // indirect
github.com/Azure/go-ansiterm v0.0.0-20250102033503-faa5f7b0171c // indirect
github.com/Microsoft/go-winio v0.6.2 // indirect
github.com/aymerick/douceur v0.2.0 // indirect
github.com/cenkalti/backoff/v4 v4.3.0 // indirect
github.com/cespare/xxhash/v2 v2.3.0 // indirect
github.com/containerd/errdefs v1.0.0 // indirect
@@ -45,6 +48,7 @@ require (
github.com/golang-jwt/jwt/v5 v5.3.1 // indirect
github.com/google/uuid v1.6.0 // indirect
github.com/googleapis/gax-go/v2 v2.19.0 // indirect
github.com/gorilla/css v1.0.1 // indirect
github.com/inconshreveable/mousetrap v1.1.0 // indirect
github.com/jackc/pgpassfile v1.0.0 // indirect
github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect
@@ -106,7 +110,6 @@ require (
go.yaml.in/yaml/v3 v3.0.5 // indirect
golang.org/x/crypto v0.57.0 // indirect
golang.org/x/image v0.46.0 // indirect
golang.org/x/net v0.58.0 // indirect
golang.org/x/sync v0.23.0 // indirect
golang.org/x/sys v0.48.0 // indirect
golang.org/x/term v0.46.0 // indirect