spotify-audio-url

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content from Spotify and various RSS feeds.
  • Ingestion points: The agent retrieves data from Spotify episode pages and dynamically discovered RSS feed URLs using web_fetch.
  • Boundary markers: The skill enforces a strict output format, requiring the agent to return only the direct audio URL or a specific, hardcoded refusal phrase. This format restricts the agent's ability to relay malicious instructions potentially embedded in the external content.
  • Capability inventory: The skill uses web_fetch and web_search tools and does not have access to file-writing, shell execution, or remote code execution capabilities.
  • Sanitization: The instructions include a specific step to clean extracted URLs by removing tracking query parameters.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 11:12 PM