doc-i18n
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external Markdown files, which constitutes a surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: Files are read from
docs/pages/anddocs/pages/zh/during the Phase 1: Analyze step (SKILL.md). - Boundary markers: The skill does not explicitly define delimiters to separate content from instructions, though it treats input as prose to be translated.
- Capability inventory: File read/write access to the documentation tree and natural language translation capabilities.
- Sanitization: There are no explicit sanitization steps mentioned for the content being processed. This is a common characteristic of translation skills and is considered low risk given the specific technical context.
Audit Metadata