veo-3
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional and does not contain any executable code, scripts, or commands. It follows a modular design pattern, delegating API interactions to a separate integration file.
- [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was found. The skill includes a 'Quality bar — self-check' and 'Edge cases & pushback' section that explicitly instructs the agent to refuse requests for generating real identifiable people or copyrighted IP, which serves as a security best practice for generative AI skills.
- [SAFE]: The skill uses local reference files (e.g., brand-profile.md) for context, which is standard behavior and does not involve accessing sensitive system paths or credentials.
Audit Metadata