skills/rtadewald/skills/mediabunny/Gen Agent Trust Hub

mediabunny

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate documentation and code snippets for the mediabunny multimedia library and the remotion framework.
  • [EXTERNAL_DOWNLOADS]: Fetches multimedia content from well-known services (e.g., remotion.media) and references official documentation at mediabunny.dev for processing. These are standard operations for the library's stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines ingestion points for external media files, but the functionality is limited to technical metadata extraction (duration and dimensions), which carries minimal risk of executing instructions embedded in file metadata.
  • Ingestion points: UrlSource(src) and FileSource(file) used in get-audio-duration.md, get-video-dimensions.md, and get-video-duration.md.
  • Boundary markers: Not present.
  • Capability inventory: Extracts technical properties using input.computeDuration() and input.getPrimaryVideoTrack().
  • Sanitization: Not present.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 12:39 AM