docu-optimizer
Pass
Audited by Gen Agent Trust Hub on Feb 27, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface.
- Ingestion points: The skill reads untrusted content from
CLAUDE.md, thedocs/directory, and project source files (to extract APIs and project stages). - Boundary markers: The instructions do not specify the use of delimiters or 'ignore embedded instructions' warnings when passing documentation content to the five subagents defined in Phase 2.
- Capability inventory: The skill utilizes tools such as
Edit,Write, andBash, which could be triggered maliciously if the agent obeys instructions hidden within documentation or code comments. - Sanitization: No sanitization or structural validation is mentioned for the content extracted from the repository before it is synthesized into a final report or an 'optimized' file version.
Audit Metadata