moai-cc-mcp-builder

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

• Third-party content exposure detected (high risk: 0.80). The skill repeatedly fetches live MCP patterns and "community" knowledge via Context7 (e.g., calls to self.context7.get_library_docs in AIMCPArchitectureDesigner, Context7AgentCentricDesigner, and multiple generate/integrate methods in SKILL.md), and that external Context7 content is read and used to drive architecture, code generation, and tooling decisions—exposing the agent to third-party content that can materially influence behavior.