ffmpeg
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains standard, well-documented FFmpeg and ffprobe command examples for legitimate media processing tasks. No evidence of malicious behavior, obfuscation, or persistence was found. All shell snippets provided are typical for video production workflows.
- [EXTERNAL_DOWNLOADS]: The skill mentions a public GitHub repository
github.com/digitalsamba/claude-code-video-toolkitfor contributions and feedback. This is a reference to an external source from a known video technology provider and does not involve automated remote code execution. - [PROMPT_INJECTION]: The skill involves an indirect prompt injection surface due to media file processing. 1. Ingestion points: Files processed via
ffmpeg -iorffprobe. 2. Boundary markers: Absent. 3. Capability inventory: Execution of media transformation and file system write operations. 4. Sanitization: None. This surface is characteristic of media tools and is assessed as safe within the context of the skill's purpose.
Audit Metadata