mixxx-ai-dj

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation references a custom fork of the Mixxx DJ software at https://github.com/tsirysndr/mixxx, which is required for MCP support. This repository is owned by the skill author.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes metadata such as artist names, track titles, and genres from music libraries.
  • Ingestion points: Track metadata is retrieved from the local library via mixxx_suggest_next and from remote Subsonic/Navidrome servers via mixxx_subsonic_browse and mixxx_subsonic_search.
  • Boundary markers: The instructions do not define specific boundary markers for handling this data.
  • Capability inventory: Capabilities are restricted to DJ software controls, including loading tracks, playback, sync, crossfading, and EQ adjustments.
  • Sanitization: No specific sanitization methods for track metadata are described.
  • Risk Assessment: While the ingested metadata is external, the skill's limited capabilities focused on media playback minimize the impact of potential injection attacks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 07:27 PM
Security Audit — agent-trust-hub — mixxx-ai-dj