content-engine

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

• Third-party content exposure detected (high risk: 0.90). The skill's required Research & Preparation step explicitly instructs the agent to "analyze ... SERP features, and top‑ranking content" and the Content Audit workflow mandates pulling a content inventory (URLs, publish dates, current traffic/rankings) from the open web (SKILL.md Research & Preparation / Secondary Workflow), which requires ingesting and interpreting public third‑party pages whose instructions or content could materially influence subsequent content‑creation decisions.