connector-spotify

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from the Spotify Web API. This content, which includes user-controlled strings like track titles and artist names, serves as a potential vector for indirect prompt injection if processed by an agent without isolation.
  • Ingestion points: External data is fetched via functions such as getTrack and getInformationAboutTheUsersCurrentPlayback as described in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat API-returned data as untrusted or to ignore embedded instructions.
  • Capability inventory: The skill enables outbound HTTPS network operations to api.spotify.com.
  • Sanitization: There are no specific instructions or code patterns for sanitizing or validating the API responses before they are interpolated into the agent's context.
  • [EXTERNAL_DOWNLOADS]: The skill requires the installation of the spotify-client package via the Motoko package manager (mops). It also references the author's own repository at github.com/caffeinelabs/skills-internal for technical reporting, which is a vendor-owned resource.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 09:46 AM
Security Audit — agent-trust-hub — connector-spotify