genmedia-video-editor

Pass

Audited by Gen Agent Trust Hub on Oct 5, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill metadata references an official Google Cloud prompting guide for the Veo model.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions involve processing user-provided media files through various tools, creating a surface for indirect prompt injection.
  • Ingestion points: Media files (video, audio, images) processed by tools referenced in SKILL.md.
  • Boundary markers: Absent.
  • Capability inventory: Video generation, format conversion, and media composition via mcp_veo and mcp_avtool tools.
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 5, 2026, 12:57 PM