wazza-sound
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements strong credential safety guidelines, specifically instructing the agent to never print, write, or request the API key within the conversation or files.
- [SAFE]: The skill addresses indirect prompt injection risks by explicitly instructing the agent to treat all data returned in reports as data rather than instructions.
- [SAFE]: Network communication is directed to the vendor's infrastructure (api-pro.wazza.ai), representing standard functionality for an API-integrated skill.
- [SAFE]: Command execution is limited to standard ffmpeg operations for audio mixing, which is consistent with the skill's stated purpose of adding sound to video.
Audit Metadata