specifying-mbd-algorithms

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 (SKILL.md Step 3: "Domain Verification" and the architecture spec's Appendix B "API Verification") explicitly instructs agents to use web_search and similar web lookups to confirm equations, standards, and API behavior—forcing the agent to fetch and interpret open/public web content that can influence decisions and tool use.