summarize

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.85). The skill’s required workflow includes summarizing arbitrary user-supplied URLs (and optionally YouTube) by fetching/extracting their page text at runtime, which is outsider-authored free-form content that can be ingested into the LLM context (public web content via URL extraction / Apify fallback).