cutting-rhythm

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the video-agent CLI tool, invoked through uv run, to execute video and audio processing tasks. This includes analyzing media files, calculating beat grids, and rendering Edit Decision Lists (EDLs). These operations involve interactions with the local file system for input/output.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for ingesting and processing external media and transcription data to create automated video edits.
  • Ingestion points: The skill processes external media files (talk.mp4, music.mp3) and transcription data (transcribe --words, speech-segments) referenced in the documentation.
  • Boundary markers: There are no explicit instructions or delimiters defined to separate user-provided data from the agent's logic.
  • Capability inventory: The skill has the ability to execute shell commands via uv run video-agent with subcommands like tighten, beats, snap, and edl.
  • Sanitization: No specific sanitization or validation steps are outlined for the external media or transcription data being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 06:10 AM
Security Audit — agent-trust-hub — cutting-rhythm