video-to-superprompt
Pass
Audited by Gen Agent Trust Hub on Aug 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill explicitly instructs the agent to execute shell commands using
ffprobeandffmpegto extract metadata and generate image frames from user-provided video files for technical analysis. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data (video files and URLs) which serves as a potential attack surface for indirect instructions hidden in video content or metadata.
- Ingestion points: Local file paths, uploaded video files, and remote URLs provided by the user.
- Boundary markers: The instructions do not specify the use of delimiters or warnings to ignore instructions embedded within the processed video data.
- Capability inventory: The skill utilizes shell execution (
ffprobe,ffmpeg), filesystem writes (creating directories in/tmp), and repository management commands (git commit). - Sanitization: No explicit sanitization or filtering of the content extracted from the video is defined before it is used to construct the final prompt.
Audit Metadata