doc-freshness-review
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process documentation files (such as those in
doc/andREADME.md) which could contain untrusted data if the repository itself is malicious. - Ingestion points: Reads files under
doc/,README.md,README.zh-CN.md,mcp/README.md, andmcp/README.zh-CN.md(identified in SKILL.md Phase 1). - Boundary markers: The instructions do not specify explicit delimiters or "ignore instructions" warnings for the content being reviewed.
- Capability inventory: The skill is restricted to generating reports, opening issues, and preparing documentation-focused Pull Requests (routed to
pr-review-fix). It lacks capabilities for arbitrary command execution or network exfiltration. - Sanitization: No specific sanitization or filtering of the documentation content is mentioned before it is processed by the agent.
- [SAFE]: The skill's operations are confined to documentation auditing and reporting within the repository scope. No high-risk behaviors such as credential access, persistence mechanisms, or obfuscation were detected.
Audit Metadata