i18n-backend
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied locale information (via
Accept-LanguageorX-Localeheaders). While this is an ingestion point for untrusted data, the instructions strictly mandate standard parsing using established language matchers and discourage direct concatenation. The risk is minimized by the primary purpose of the skill (i.e., localization logic).
Audit Metadata