build

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflow explicitly instructs the agent to perform "web search" and "Web search for implementation specifics" during "Conduct Deep Research" and "Deep Research on Phase" (and to include external "References" links), meaning it will fetch and read untrusted public web content that can influence implementation decisions and actions.