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 ffprobe and ffmpeg to 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
Risk Level
SAFE
Analyzed
Aug 30, 2026, 02:54 PM
Security Audit — agent-trust-hub — video-to-superprompt