contract-review
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data in the form of legal contracts (MSAs, NDAs, SOWs, etc.), creating a potential surface for indirect prompt injection attacks where malicious text embedded in a contract could attempt to override the agent's instructions.
- Ingestion points: Document content provided by the user via file attachments or pasted text, as described in the skill description and verified in test cases within
evals/evals.json. - Boundary markers: Absent. The instructions do not specify the use of delimiters or specific instructions to the agent to treat the document text solely as data and ignore any embedded commands.
- Capability inventory: The skill instructs the agent to create and save markdown files in the local working folder.
- Sanitization: Absent. The skill does not include any logic for filtering or sanitizing the input text before processing it for legal risks.
Audit Metadata