deepwiki
Warn
Audited by Snyk on Feb 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill fetches and reads documentation from public third‑party sites—notably deepwiki.com via WebFetch/MCP and fallback access to public GitHub repos/READMEs via the gh API—which are untrusted, user‑generated sources the agent will ingest and interpret.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches runtime content from https://deepwiki.com/owner/repo (via WebFetch) and registers/uses MCP endpoints at https://mcp.deepwiki.com/mcp and https://mcp.deepwiki.com/sse to provide remote tools, so external content at these URLs directly drives prompts and supplies remote-executed tool behavior.
Audit Metadata