utility-pm-skill-iterate
Pass
Audited by Gen Agent Trust Hub on Oct 18, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process potentially untrusted data from external validation reports and user feedback (SKILL.md, Step 3) to generate proposed modifications to skill files.\n
- Ingestion points: Untrusted data enters the agent's context through validation reports (parsed for recommendations) and free-text user feedback provided in Step 3.\n
- Boundary markers: The skill instructions do not specify the use of clear delimiters or instructions to ignore embedded commands within the processed inputs.\n
- Capability inventory: The skill possesses the capability to read from and write to the local filesystem (SKILL.md, Steps 2 and 5).\n
- Sanitization: There is no mention of explicit sanitization, escaping, or filtering of the content extracted from the validation reports or feedback before it is used to generate file edits. However, the multi-step confirmation process and human-in-the-loop preview (Step 4) serve as a primary security control.
Audit Metadata