collecting-intelligence
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructional content for business strategy research, primarily involving documentation tasks.
- [SAFE]: File system access is limited to reading project context and writing strategy deliverables, aligning with the skill's stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from project context files (e.g., 'my-gtm-context.md') and Phase 1 outputs. Ingestion points: Reads project root context and Phase 1 output files. Boundary markers: None. Capability inventory: File-write access to the outputs directory. Sanitization: None. The risk is minimal as the skill does not invoke executable tools or perform network operations.
- [SAFE]: External links point to well-known research platforms (e.g., Meta Ads Library, Google Ads Transparency Center) or the author's official domain ('gtmstrategist.com').
Audit Metadata