stp-marketing
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external market research summaries and data, which introduces a potential surface for indirect prompt injection. \n
- Ingestion points: Market research summaries provided by the user and content retrieved via WebFetch. \n
- Boundary markers: The skill instructions include a comprehensive evidence ladder and verification checklist to evaluate data quality. \n
- Capability inventory: Tool access is limited to information retrieval (Read, Grep, WebSearch, WebFetch). \n
- Sanitization: Guidelines explicitly require labeling evidence provenance and exclude personal, sensitive, or confidential data.
Audit Metadata