blog

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow (Step 1: "Keyword Research") explicitly instructs the agent to perform web searches and "check what's currently ranking" and the "Resources" section requires adding external links and cited statistics, so the agent must fetch and interpret open/public third‑party web content (untrusted) that will directly influence keyword selection and writing decisions.