mcp-deepwiki

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

• Third-party content exposure detected (high risk: 0.90). The skill uses the DeepWiki MCP tools (mcp__deepwiki__read_wiki_structure, mcp__deepwiki__read_wiki_contents, mcp__deepwiki__ask_question) to fetch and read documentation and AI-generated content for arbitrary GitHub repositories (owner/repo), which are public, user-controlled third-party sources and thus can contain untrusted content that the agent will read and interpret.