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_fetch operations 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_fetch and web_search tools 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
Risk Level
SAFE
Analyzed
Aug 28, 2026, 10:17 PM
Security Audit — agent-trust-hub — spotify-audio-url