deep-wiki

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

• Third-party content exposure detected (high risk: 0.80). The skill calls the external DeepWiki MCP endpoint (https://mcp.deepwiki.com/mcp) to fetch AI-generated documentation for arbitrary public GitHub repositories (SKILL.md and scripts/deepwiki.ts), so it ingests untrusted, user-generated third-party content that the agent reads and could materially influence subsequent actions.