learn

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

• Third-party content exposure detected (high risk: 0.80). The skill's Phase 1 "Collect" workflow explicitly instructs discovering arbitrary public URLs (via installed search plugins or the environment's web search) and fetching them through the /read tool (saving pages like blogs, papers, repos to ~/Downloads/{title}.md), so the agent will ingest untrusted third‑party web content that can influence subsequent decisions and actions.