summarize

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

• Third-party content exposure detected (high risk: 0.85). The skill’s runtime path includes fetching and extracting readable text from user-supplied URLs (public web content) and optionally YouTube transcripts via external services (e.g., Apify), which are outsider-authored free text that can be fed into the agent’s LLM context.