connector-spotify
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from the Spotify Web API (track names, artist information, and player states), which represents untrusted external content that could be manipulated by a third party to influence the agent.
- Ingestion points: Data is fetched from the Spotify Web API through the
mo:spotify-clientpackage, specifically through modules likeTracksApiandPlayerApi(e.g.,getTrack,getInformationAboutTheUsersCurrentPlayback). - Boundary markers: No specific delimiters or "ignore instructions" warnings are defined in the instructions for how the agent should handle the data retrieved from Spotify endpoints.
- Capability inventory: The skill is designed to perform outbound HTTPS requests to
api.spotify.comand manipulate user playback states (play, pause, skip) via bearer tokens. - Sanitization: There is no evidence of sanitization or filtering of the textual data returned by the API (such as track metadata or artist biographies) before it is provided to the agent for processing.
Audit Metadata