diligence-evidence-matrix
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes external documents including contracts, scans, and corporate records which are ingestion points for untrusted data.
- Ingestion points: Project directories, legal documents, PDF/scanned files, and the
corporate-legal/CLAUDE.mdworkspace file. - Boundary markers: The instructions do not specify the use of delimiters or boundary markers when reading raw document content.
- Capability inventory: The skill reads files from the local filesystem and generates structured matrices based on that content.
- Sanitization: There is no evidence of sanitization or escaping mechanisms for external content before it is processed by the agent.
Audit Metadata