moai-foundation-core

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly delegates to external MCP integrators (e.g., mcp-context7 and mcp-playwright) in modules/agents-reference.md and delegation examples — including calls like "Research React 19 APIs" and browser automation — which shows it fetches/ingests public third-party documentation/pages that the agent reads and uses to drive subsequent Agent() decisions.