autonomous-investigation
Pass
Audited by Gen Agent Trust Hub on Jul 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill acts as a methodology and documentation framework (protocol) for other research tasks and does not include any executable scripts, binary files, or automated tool configurations.
- [EXTERNAL_DOWNLOADS]: References an external GitHub repository belonging to the author (
github.com/deanpeters/product-manager-prompts) as a source for the investigation contract. This is a reference to a well-known service and represents a vendor-owned resource. - [DATA_EXFILTRATION]: Contains a dedicated guardrails section that explicitly prohibits unethical collection methods such as pretexting, soliciting NDA-protected information, or violating site terms of service.
- [PROMPT_INJECTION]: Instructions focus on improving the quality and honesty of AI research (e.g., 'do-not-invent' lists) rather than attempting to bypass safety filters or override system instructions.
Audit Metadata