predict
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-supplied proposals and project documentation, which is a standard ingestion point for untrusted data.\n
- Ingestion points: The input and local files like AGENTS.md and PLAN.md.\n
- Boundary markers: None present.\n
- Capability inventory: The skill is restricted to reasoning; no network or shell capabilities are used.\n
- Sanitization: None.\n- [SAFE]: No malicious patterns such as obfuscation, credential theft, or unauthorized command execution were detected. The skill safely references external projects for documentation purposes and explicitly instructs the agent to ensure secrets are not leaked to logs.
Audit Metadata