contract-review
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill reviews untrusted contract text, which allows for potential indirect prompt injection attacks where malicious instructions are hidden in a document.
- Ingestion points: Contract text provided by the user in the chat session.
- Boundary markers: Absent. The skill does not use specific markers to separate the contract data from its instructions.
- Capability inventory: No sensitive capabilities detected; the skill only generates text.
- Sanitization: Absent. No sanitization of user-provided text is performed.
Audit Metadata