deepwiki-mcp-skill

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

• Third-party content exposure detected (low risk: 0.10). The workflow queries and reads wiki documentation from GitHub repositories via the DeepWiki MCP service, which constitutes reading external repository contents and documentation (low risk as the agent selects specific repositories/URLs to fetch).

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill references an external install script on GitHub for uxc under an arbitrary personal/community organization (holon-run), which constitutes an unverified runtime external dependency.