map-use-cases
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data from repository code and artifacts to map use cases.
- Ingestion points: Step 1 and 2 in SKILL.md involve reading repository instructions, artifacts, domain docs, and referenced code.
- Boundary markers: Explicit instructions state 'Produce use-case documentation only: never implement behavior, create tests, or modify application code' and 'forbid edits and implementation.'
- Capability inventory: Writing documentation files to the local filesystem (docs/use-cases/).
- Sanitization: Includes a mandatory independent audit step to reconcile conflicts and omissions before finalizing documentation.
Audit Metadata