update-claudemd
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes existing project documentation to generate updates.
- Ingestion points: The agent reads the project's CLAUDE.md and all files within the .claude/claudemd-topics/ directory during the research phase (Phase 2).
- Boundary markers: Absent; the instructions do not specify the use of delimiters or 'ignore' instructions for the content read from the repository.
- Capability inventory: The skill is authorized to use Write and Edit tools for file modification, as well as Bash for git history, directory creation, and file copying.
- Sanitization: The skill includes a mandatory human-in-the-loop validation step (Phase 5) where it uses the AskUserQuestion tool to present all proposed changes for user approval before execution.
Audit Metadata