media-mkvtoolnix

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a Python script (scripts/mkv.py) to wrap MKVToolNix command-line utilities. These utilities are executed via subprocess.run using list-based arguments, which follows security best practices to prevent shell injection.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it processes untrusted data from media files and user-provided metadata strings.
  • Ingestion points: User-supplied arguments for file paths, track names, and metadata in scripts/mkv.py.
  • Boundary markers: Absent. The skill does not explicitly instruct the agent to ignore potentially malicious instructions embedded in file metadata.
  • Capability inventory: The skill can read, write, and modify files on the file system via mkvmerge, mkvextract, and mkvpropedit calls in scripts/mkv.py.
  • Sanitization: Arguments are handled as a list in subprocess.run, and the script uses shlex.quote for logging purposes, providing defense against shell command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 09:54 AM
Security Audit — agent-trust-hub — media-mkvtoolnix