remotion-multimedia

Pass

Audited by Gen Agent Trust Hub on Nov 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill consists of legitimate documentation and utility functions for media analysis. No malicious patterns such as obfuscation, credential theft, or unauthorized persistence were identified.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted media data, which is an inherent risk for indirect prompt injection via media metadata. However, this is consistent with the skill's primary purpose. 1. Ingestion points: Media file parsing in get-audio-duration.md, get-video-dimensions.md, and get-video-duration.md. 2. Boundary markers: None present in the utility function wrappers. 3. Capability inventory: Local file system access and network requests provided via the Mediabunny input sources. 4. Sanitization: Not explicitly implemented in the skill code; relies on the underlying library's parsing logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 13, 2026, 12:21 AM