product-manager
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data during market research, competitive analysis, and user research tasks.
- Ingestion points: SKILL.md specifies gathering industry trends, competitor features, user reviews, and testimonials via web search.
- Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded in the external research data.
- Capability inventory: The skill analyzes data to generate PRDs, roadmaps, and user stories. It also references local helper scripts
scripts/analyze-market.shandscripts/generate-stories.shto facilitate these tasks. - Sanitization: There are no mentioned mechanisms for sanitizing, filtering, or escaping external content before it is processed by the agent.
Audit Metadata