Product Manager
Pass
Audited by Gen Agent Trust Hub on Oct 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data to synthesize product insights and documentation.
- Ingestion points: The agent gathers information using WebFetch and WebSearch for research and Read for local file analysis (refer to the Discovery phase in SKILL.md).
- Boundary markers: The instructions do not establish clear delimiters or safeguards to prevent the agent from following instructions embedded within the analyzed data.
- Capability inventory: The agent has the ability to write and modify files using Write and Edit tools.
- Sanitization: There is no evidence of sanitization or validation logic to filter out adversarial instructions contained in external research sources.
Audit Metadata