veo3-video-gen
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [SAFE]: The skill performs its stated function of video generation using official APIs from a trusted vendor. Analysis found no evidence of prompt injection, data exfiltration, or persistence mechanisms.
- [COMMAND_EXECUTION]: The skill executes a bundled Python script (
generate_video.py) through theuvpackage manager and invokesffmpegfor media concatenation. These commands are necessary for the skill's media processing features. - [EXTERNAL_DOWNLOADS]: The skill makes network requests to Google's Gemini API endpoints. As Google is a trusted well-known service, these interactions are considered safe and consistent with the skill's purpose.
Audit Metadata