managing-sources

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs agents to add and fetch arbitrary public source URLs and to scrape/render their pages (see "Add source", "Fetch releases", "evaluate_url", "Rendering Control", and the "Playbooks" sections), so untrusted third-party web content is ingested and used to guide parsing and agent actions.