review-contract
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted external data (contracts provided via file upload, URL, or text) which constitutes an indirect prompt injection surface.
- Ingestion points: User-supplied contracts in Step 1 of
SKILL.md. - Boundary markers: The prompt does not specify the use of delimiters or 'ignore' instructions to isolate contract text from analysis instructions.
- Capability inventory: The skill uses
Read,Glob, andGreptools to access filesystem data and configurations. - Sanitization: No content validation or sanitization of the input text is performed before it is analyzed by the agent.
Audit Metadata