developing-with-ai

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

• Third-party content exposure detected (high risk: 0.80). The INSTRUCTIONS.md and references (e.g., "Option 2: External Wiki" in references/CONTEXT-ENGINEERING.md and the MCP/registry URL and AgentCard/AGENTS.md examples in references/AGENT-AND-PROJECT.md) explicitly describe using external public URLs and registries as context sources that agents are expected to read and act on, so untrusted third‑party content could influence agent decisions.