deep-wiki

Warn

Audited by Snyk on Mar 7, 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 explicitly contacts DeepWiki's MCP server (https://mcp.deepwiki.com/sse) to produce AI-generated documentation and answers for any public GitHub repository (see SKILL.md and references/api_reference.md stating "Supports any public GitHub repository" and "Only works with public GitHub repositories"), so it ingests untrusted, user-generated third-party content from arbitrary public repos that can materially influence responses and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 7, 2026, 04:54 AM