contract-review
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to intake and process external, untrusted contract documents, which could potentially contain malicious instructions intended to manipulate the agent's analysis.
- Ingestion points: As described in the Workflow and Context Required sections of SKILL.md, the agent receives contract text directly from the user for analysis.
- Boundary markers: The skill instructions do not define clear delimiters or specific instructions for the agent to ignore any embedded commands within the contract text.
- Capability inventory: The skill does not request access to any tools or perform high-risk operations such as network requests, shell command execution, or file system modifications.
- Sanitization: There is no evidence of input validation, schema enforcement, or filtering for the user-provided content before it is processed.
Audit Metadata