update-docs
Pass
Audited by Gen Agent Trust Hub on Nov 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from the repository (Markdown files, roadmaps, and git logs) which could contain malicious instructions designed to influence the agent's behavior. Ingestion points: Reads local documentation files and git history in SKILL.md (Step 1, 1.5, 1.6) and references/roadmap-freshness.md. Boundary markers: No explicit delimiters or warnings to ignore embedded instructions are used when processing file content. Capability inventory: The skill is capable of modifying files and committing changes to the repository via the git tool as described in SKILL.md (Step 8). Sanitization: No sanitization or filtering of the ingested content is performed before it is processed by the agent.
- [DYNAMIC_EXECUTION]: The skill uses a shell heredoc to execute an embedded Python script for verifying internal links. Evidence: SKILL.md (Step 5) uses python3
- <<'PYLINK' to run an inline script that validates Markdown links.
Audit Metadata