add-music-track

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes ffmpeg and ffprobe to process media files. It takes user-provided paths for video and music inputs. While the instructions are for technical media processing, security depends on the execution environment sanitizing these paths to prevent potential shell injection.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it reads metadata from external media files using ffprobe. Maliciously crafted metadata (such as ID3 tags) could theoretically contain instructions intended to influence the agent, although the skill currently uses this data only for technical verification like duration and loudness measurement.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:06 PM
Security Audit — agent-trust-hub — add-music-track