analyze

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (Phase 1 "Context gathering" and the Evidence grounding techniques) explicitly instructs using tools like WebSearch and Read/Grep/Glob to gather evidence from external/public web pages and documents, so the agent will ingest untrusted third-party content that can influence its analysis and actions.