docs-review
Pass
Audited by Gen Agent Trust Hub on Aug 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes untrusted documentation files and pull request diffs that could contain malicious instructions. \n
- Ingestion points: Markdown files and git diffs accessed through file reading tools and GitHub MCP tools. \n
- Boundary markers: The instructions lack explicit delimiters or warnings for the agent to ignore instructions embedded within the documentation content being reviewed. \n
- Capability inventory: The skill has access to the
Bashshell and several GitHub tools capable of creating and submitting pull request reviews. \n - Sanitization: There is no evidence of filtering, escaping, or validation of the content ingested from the documentation files.
Audit Metadata