Make B-roll Talking Head
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or unauthorized operations were detected. The skill acts as a standard interface for the Agent Media video processing service.
- [PROMPT_INJECTION]: The instructions are purely functional and descriptive of the video generation task. No attempts to override safety filters, bypass constraints, or extract system prompts were found.
- [CREDENTIALS_UNSAFE]: The skill references an API key using the environment variable placeholder '$AGENT_MEDIA_API_KEY'. This is the standard and safe way to document authentication without exposing actual secrets.
- [DATA_EXFILTRATION]: Network requests are directed to 'api.agent-media.ai', which is the legitimate service endpoint for the agent-media toolset. No unauthorized data harvesting or exfiltration patterns were identified.
Audit Metadata