discovery-interview-prep
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks detected. The skill acts as a text-based interactive assistant for product management research.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user input regarding product context and research goals.
- Ingestion points: SKILL.md (interactive inputs for research goals and segments).
- Boundary markers: Not present.
- Capability inventory: None (the skill does not use network, file system, or shell capabilities).
- Sanitization: Not present.
- Reasoning: The lack of dangerous capabilities makes this surface low-risk.
Audit Metadata