market-research
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from web searches and user interviews, which presents an attack surface for indirect prompt injection. 1. Ingestion points: Web content retrieved via WebReader and user-provided interview transcripts. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the ingested data are present. 3. Capability inventory: The skill has file-write capabilities (generating reports in docs/product/.ompm/) and access to web tools. 4. Sanitization: No explicit sanitization or filtering of external content is defined in the instructions.
- [SAFE]: The skill implements strict anti-hallucination rules, mandating that all market data must be sourced from recent web searches with verifiable URLs and confidence ratings.
- [SAFE]: The persistence mechanism described is restricted to the project directory and is used for cross-session research context, representing standard functional state management.
Audit Metadata