genmedia-video-editor
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions for legitimate video editing and composition tasks using dedicated tools.
- [EXTERNAL_DOWNLOADS]: The skill refers to an official Google Cloud prompting guide. This reference is documented neutrally as it originates from a trusted organization.
- [INDIRECT_PROMPT_INJECTION]: The skill possesses an ingestion surface for external media files which could theoretically contain adversarial content, though no specific vulnerabilities in how the model handles this data were found. 1. Ingestion points: Media files processed via mcp-avtool-go and mcp-veo-go tools (SKILL.md). 2. Boundary markers: None explicitly mentioned for media content. 3. Capability inventory: Media manipulation via FFmpeg and generative video APIs (SKILL.md). 4. Sanitization: None explicitly described.
Audit Metadata