mkv-track-list

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to invoke mkvmerge and mkvinfo for media container inspection. This is standard behavior for the stated purpose of analyzing MKV file metadata.\n- [PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and displays untrusted metadata (track names, titles, and language tags) from external MKV files.\n
  • Ingestion points: Track names and titles read from MKV files processed by mkvmerge (SKILL.md).\n
  • Boundary markers: None present in the parsing or display logic.\n
  • Capability inventory: Restricted to media inspection via Bash; no network or unauthorized file system write capabilities detected.\n
  • Sanitization: Metadata strings are extracted and formatted into a table without sanitization or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 03:34 PM
Security Audit — agent-trust-hub — mkv-track-list