video
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides structured guidelines for video generation tasks without any malicious patterns detected. It emphasizes defensive coding, operational security, and deterministic execution.
- [INDIRECT_PROMPT_INJECTION]: The framework explicitly recognizes risks from untrusted external inputs (e.g., via BrowserOS) and mandates the redaction of sensitive data (secrets/PII), which is a security best practice for agents processing third-party content.
- [COMMAND_EXECUTION]: The instructions require the use of an ExecutionProxy Interface (e.g., rtk npm test) for terminal operations, ensuring that command execution occurs within the boundaries of defined project protocols.
Audit Metadata