processing-video
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues were identified in the skill instructions or command templates. The skill adheres to its stated purpose of providing media processing utilities and follows best practices for using local file paths.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided media files, which represents an attack surface for indirect prompt injection via malformed media metadata.
- Ingestion points: User-provided input files in processing commands (SKILL.md).
- Boundary markers: Not specified for media stream data.
- Capability inventory: File reading/writing and subprocess execution for media transformation.
- Sanitization: Not specified, but standard ffmpeg usage generally isolates media parsing from agent instruction logic.
Audit Metadata