workflow-research

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

• Third-party content exposure detected (high risk: 1.00). The SKILL.md explicitly mandates a /web-research step and describes "gather web sources" and "cite sources for every claim," so the agent will fetch and interpret content from open/public web sources as part of its workflow (SKILL.md: "Activate the research workflow" and the required /web-research → /deep-research steps).