iopho-audio-director

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses ffmpeg via the Bash tool to perform audio manipulation tasks such as trimming, sidechain compression for ducking, and loudness normalization as described in SKILL.md and references/audio-recipes.md.- [PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes untrusted project storyboards and audio metadata.
  • Ingestion points: Ingests storyboard files and external audio files (audio.mp3) during the plan and analyze modes.
  • Boundary markers: No specific boundary markers or 'ignore' instructions are provided to the agent for isolating these external inputs.
  • Capability inventory: The skill is authorized to use Bash(ffmpeg), Bash(python3), and Bash(pip) which provide significant system access.
  • Sanitization: No validation or sanitization routines are specified for the incoming storyboard text or audio file metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 04:33 AM