privacy-policy-generator
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied business descriptions, data categories, and processing purposes to generate customized legal documents, creating an interface for potential indirect prompt injection.
- Ingestion points: The agent collects user-provided information about business operations, data types, and third-party sharing in Step 1-4 of the Quick Start and across both core workflows.
- Boundary markers: There are no explicit delimiters or instructions defined to help the agent distinguish between the user's data and its own core document-generation instructions.
- Capability inventory: The skill is restricted to text generation for policies and terms; it does not utilize high-risk tools for file system access, network operations, or command execution.
- Sanitization: The instructions do not specify any validation or sanitization steps for the agent to perform on the user-provided data before incorporating it into the final output.
Audit Metadata