lov-media-creator

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes the Python subprocess module across several scripts (e.g., audio_qc.py, media_probe.py, subtitle_gate.py) to execute external binaries including ffmpeg and ffprobe. These tools are used for essential media processing tasks such as stream inspection, transcoding, and audio loudness measurement.
  • [EXTERNAL_DOWNLOADS]: As part of the 'pip-research' workflow described in references/pip-research.md, the skill automates browser sessions to capture screenshots of third-party websites. This involves fetching content from external, untrusted URLs based on product names detected in the video subtitles.
  • [SAFE]: The skill implements a secure profile management system in scripts/profile_store.py. It includes a hardcoded blacklist (SENSITIVE_PARTS) that prevents the storage of sensitive information such as 'token', 'secret', 'password', 'credential', and 'api_key' in the user's persistent profile files.
  • [SAFE]: Instructions within the skill and its documentation (e.g., references/user-profile.md) explicitly state that source code must remain portable and must not contain hardcoded absolute paths or credentials.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 12:55 AM
Security Audit — agent-trust-hub — lov-media-creator