spotify-audio-url
Pass
Audited by Gen Agent Trust Hub on Aug 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data by fetching and parsing content from Spotify pages and third-party RSS feeds. While it identifies an attack surface for indirect prompt injection, the risk is minimized by the skill's strict output constraints, which require the agent to return only a raw URL or a specific fixed refusal string.
- Ingestion points:
web_fetchoperations on user-provided Spotify URLs and discovered RSS feed XML files. - Boundary markers: The skill contains strict instructions to return "ONLY the direct URL" or a specific fixed phrase, which acts as a logical boundary for the model's behavior.
- Capability inventory: The skill uses
web_fetchandweb_searchtools but specifically disables file writing (writes-files: false). - Sanitization: The instructions include specific steps to clean query strings from URLs and match episode titles/dates to ensure data integrity.
Audit Metadata