Use restricted sanitizer for repository description (#28141)

- Currently the repository description uses the same sanitizer as a
normal markdown document. This means that element such as heading and
images are allowed and can be abused.
- Create a minimal restricted sanitizer for the repository description,
which only allows what the postprocessor currently allows, which are
links and emojis.
- Added unit testing.
- Resolves https://codeberg.org/forgejo/forgejo/issues/1202
- Resolves https://codeberg.org/Codeberg/Community/issues/1122

(cherry picked from commit 631c87cc2347f0036a75dcd21e24429bbca28207)

Co-authored-by: Gusted <postmaster@gusted.xyz>

1 files changed, 32 insertions, 3 deletions

diff --git a/modules/markup/sanitizer.go b/modules/markup/sanitizer.go
index 48c08831f1..992e85b989 100644
--- a/modules/markup/sanitizer.go
+++ b/modules/markup/sanitizer.go
@@ -18,9 +18,10 @@ import (
 // Sanitizer is a protection wrapper of *bluemonday.Policy which does not allow
 // any modification to the underlying policies once it's been created.
 type Sanitizer struct {
-	defaultPolicy    *bluemonday.Policy
-	rendererPolicies map[string]*bluemonday.Policy
-	init             sync.Once
+	defaultPolicy     *bluemonday.Policy
+	descriptionPolicy *bluemonday.Policy
+	rendererPolicies  map[string]*bluemonday.Policy
+	init              sync.Once
 }
 
 var (
@@ -41,6 +42,7 @@ func NewSanitizer() {
 func InitializeSanitizer() {
 	sanitizer.rendererPolicies = map[string]*bluemonday.Policy{}
 	sanitizer.defaultPolicy = createDefaultPolicy()
+	sanitizer.descriptionPolicy = createRepoDescriptionPolicy()
 
 	for name, renderer := range renderers {
 		sanitizerRules := renderer.SanitizerRules()
@@ -161,6 +163,27 @@ func createDefaultPolicy() *bluemonday.Policy {
 	return policy
 }
 
+// createRepoDescriptionPolicy returns a minimal more strict policy that is used for
+// repository descriptions.
+func createRepoDescriptionPolicy() *bluemonday.Policy {
+	policy := bluemonday.NewPolicy()
+
+	// Allow italics and bold.
+	policy.AllowElements("i", "b", "em", "strong")
+
+	// Allow code.
+	policy.AllowElements("code")
+
+	// Allow links
+	policy.AllowAttrs("href", "target", "rel").OnElements("a")
+
+	// Allow classes for emojis
+	policy.AllowAttrs("class").Matching(regexp.MustCompile(`^emoji$`)).OnElements("img", "span")
+	policy.AllowAttrs("aria-label").OnElements("span")
+
+	return policy
+}
+
 func addSanitizerRules(policy *bluemonday.Policy, rules []setting.MarkupSanitizerRule) {
 	for _, rule := range rules {
 		if rule.AllowDataURIImages {
@@ -176,6 +199,12 @@ func addSanitizerRules(policy *bluemonday.Policy, rules []setting.MarkupSanitize
 	}
 }
 
+// SanitizeDescription sanitizes the HTML generated for a repository description.
+func SanitizeDescription(s string) string {
+	NewSanitizer()
+	return sanitizer.descriptionPolicy.Sanitize(s)
+}
+
 // Sanitize takes a string that contains a HTML fragment or document and applies policy whitelist.
 func Sanitize(s string) string {
 	NewSanitizer()