video-quality-review
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides instructions to run a shell command using ffprobe for technical inspection of video files. Evidence: references/guide.md recommends the command 'ffprobe -v error -show_format -show_streams -of json output.mp4' to read metadata.
- [INDIRECT_PROMPT_INJECTION]: The workflow involves processing external data in the form of video metadata, which can be manipulated to include malicious instructions targeting the agent. Ingestion points: Video metadata ingested via ffprobe in references/guide.md. Boundary markers: The instructions do not define specific delimiters or warnings to isolate external metadata from the agent's control logic. Capability inventory: The skill utilizes shell command execution via ffprobe. Sanitization: No explicit sanitization or filtering of the ffprobe JSON output is mentioned before it is interpreted by the agent.
Audit Metadata