influencer-agreement-review
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze user-supplied legal documents, which provides a pathway for indirect prompt injection attacks where instructions hidden in the contract could attempt to influence the agent's behavior. \n
- Ingestion points: The skill analyzes external contract files during both the CHECK (audit) and ADVISE (consultation) modes. \n
- Boundary markers: The instructions do not define clear delimiters or specific instructions to the agent to disregard commands embedded within the text of the agreement. \n
- Capability inventory: The skill is purely informational; it does not request tool access or include scripts, meaning it cannot execute code, access the filesystem, or perform network operations. \n
- Sanitization: The skill does not include any mechanisms for sanitizing or filtering the content of the analyzed documents.
Audit Metadata