content-brief

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

• Third-party content exposure detected (high risk: 1.00). The skill's required Process steps 2–3 ("Research keyword landscape" and "Analyze top-ranking content for the target keyword") and the "Competitive URLs" input explicitly require ingesting and interpreting top-ranking/public competitor webpages, exposing the agent to untrusted third‑party web content that can influence decisions.