free-tools
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill directs the agent to read business context from local files, establishing an ingestion point for untrusted data that could influence agent behavior. \n
- Ingestion points: The 'Initial Assessment' section in
SKILL.mdidentifies.agents/product-marketing.md,.claude/product-marketing.md, andproduct-marketing-context.mdas data sources for context gathering. \n - Boundary markers: The instructions do not define delimiters or specific safety markers to differentiate between the context file's data and its own instructions. \n
- Capability inventory: The skill is primarily focused on strategic advice and does not include scripts for code execution, network operations, or sensitive file access. \n
- Sanitization: No logic for sanitizing or filtering the content of the ingested context files is provided.
Audit Metadata