build

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

• Third-party content exposure detected (high risk: 0.75). The required workflow explicitly instructs “Web search” during the research/phase steps (e.g., SKILL.md:138-141 and SKILL.md:508-510), which at runtime can fetch/ingest public web page text (outsider-authored free-form content) into the agent context for summarization/planning.