spotify
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard command-line tools like
curlandjqto interact with the Spotify Web API and process JSON responses. - [EXTERNAL_DOWNLOADS]: Retrieves music metadata and user profile information from official Spotify API endpoints at
api.spotify.com. - [DATA_EXFILTRATION]: Accesses the
SPOTIFY_TOKENenvironment variable and retrieves user-specific data (such as top tracks and listening history) as required for the skill's intended functionality. - [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from the Spotify catalog which constitutes a potential injection surface for untrusted strings (e.g., track titles or artist names).
- Ingestion points: API responses from Spotify are processed in
SKILL.mdviacurlandjq. - Boundary markers: Not explicitly used to separate retrieved data from agent instructions.
- Capability inventory: Restricted to network requests via
curland local file writing to/tmp/for query construction. - Sanitization: Standard
jqparsing is used but no specific content filtering for the LLM is performed.
Audit Metadata