rea-video-reverse-engineer
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
ffmpegandffprobeto analyze video files and detect scene transitions. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data, including video files, website URLs, and application binaries.
- Ingestion points: Local video files (
reference.mp4), live website URLs, and application binaries. - Boundary markers: The instructions do not define clear boundaries or 'ignore' instructions for the data being processed.
- Capability inventory: The skill utilizes FFmpeg for video processing and a local toolkit (
rea/) for JS, WASM, and native code analysis. - Sanitization: There is no evidence of input validation or sanitization for the files or URLs processed.
- [EXTERNAL_DOWNLOADS]: The skill references an external repository (
github.com/morluto/rea) as the source for the REA toolkit used in its analysis workflows.
Audit Metadata