cli-anything-vlc

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill wraps VLC functionality using a subprocess backend to execute media management commands. This is consistent with its stated purpose as a CLI wrapper and does not involve arbitrary or unsafe command execution.
  • [EXTERNAL_DOWNLOADS]: The documentation references installing the VLC application via Homebrew and the python-vlc library via pip. These are legitimate dependencies from well-known and reputable sources (VideoLAN and the official Python Package Index).
  • [PROMPT_INJECTION]: The skill retrieves media metadata and file lists, which constitutes an ingestion point for untrusted data that could be leveraged for indirect prompt injection.
  • Ingestion points: Output from commands such as playback-list, playlist-list, and info-get as seen in SKILL.md and references/commands.md.
  • Boundary markers: Absent; there are no specific instructions to delimit or ignore instructions found within media metadata.
  • Capability inventory: The skill has the ability to manage playback, streams, and transcoding via subprocess calls.
  • Sanitization: The skill does not perform sanitization of ingested media metadata before presenting it to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 06:11 PM
Security Audit — agent-trust-hub — cli-anything-vlc