produce-video

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [SAFE]: The skill acts as an orchestrator, delegating specific tasks to other local skills (narrate, film-demo, sync-narration) through a defined pipeline. Analysis of the orchestration logic shows no attempts to bypass safety or exfiltrate data.\n- [COMMAND_EXECUTION]: The instructions involve executing local Python and Node.js scripts using paths relative to other skill directories (e.g., python <narrate-skill-dir>/scripts/generate_narration.py). This is a standard orchestration pattern for modular skill design.\n- [EXTERNAL_DOWNLOADS]: Includes a pip install command targeting a requirements file within a companion skill's directory (pip install -r <sync-narration-skill-dir>/scripts/requirements.txt). This facilitates environment setup for the necessary processing tools and targets local configuration.\n- [DATA_EXPOSURE]: Uses /tmp/ for temporary storage of narration text (/tmp/say.txt) and alignment data (/tmp/aligned.json). This is standard practice for transient data and does not involve access to sensitive user credentials or system files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 12:54 PM