deep-reading-analyst

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly accepts user-provided URLs/long-form content and in "Level 4 (Research
• 120min+)" states it will perform web_search to find and load 2–3 related sources for cross-source comparison, which means it ingests arbitrary public web content (untrusted third-party/user-generated) that the agent will read and interpret as part of its workflow.