msw-search

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly calls external services—the msw-mcp vector retrievers (mlua_api_retriever / mlua_document_retriever) and the public Resources API at https://resourcesearch-api.future.msw.nxdev.kr via plugins/msw-maker-base-skill/skills/msw-search/msw_resource_api.cjs—to fetch document content, code examples, AI-generated tags, and user-uploaded resources (RUIDs) which the agent must read and then use to drive actions (e.g., choosing RUIDs, converting examples, assigning assets), so untrusted third‑party content can directly influence tool use and behavior.