spotify

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references a setup guide at https://hermes-agent.nousresearch.com/docs/user-guide/features/spotify. This is a legitimate documentation resource for the Hermes Agent ecosystem and aligns with the skill author's identity.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by processing external Spotify metadata which is not controlled by the agent.
  • Ingestion points: Data is received from the Spotify API via spotify_search, spotify_playlists, and spotify_playback (specifically the recently_played action) as documented in SKILL.md.
  • Boundary markers: None are defined; the skill does not explicitly instruct the agent to use delimiters or ignore instructions embedded in song titles or playlist names.
  • Capability inventory: The skill has the ability to modify the user's Spotify account state, including starting/stopping playback, creating playlists, and modifying library content via the spotify_playback and spotify_playlists tools.
  • Sanitization: The skill instructions do not specify any sanitization for retrieved metadata strings before they enter the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 05:58 AM