terms-of-service
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data from the
startup-contextand direct user input to generate legal documents. This creates a surface for indirect prompt injection where malicious content in the startup context could attempt to influence the agent's behavior. - Ingestion points: Reads from the
startup-contextfile and accepts open-ended user descriptions of product features and interactions. - Boundary markers: Absent. The instructions do not specify delimiters or provide guidance to the agent on how to isolate untrusted data from its primary instructions.
- Capability inventory: The skill is limited to text generation and does not utilize any tools for network access, file system modifications, or command execution.
- Sanitization: No sanitization or validation logic is defined for the external inputs.
Audit Metadata