researching-with-deepwiki

Warn

Audited by Snyk on Oct 30, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (low risk: 0.10). The agent actively searches and fetches repository codebases and documentation via the DeepWiki MCP server based on specific user requests, making it a low-risk ingestion of external content.

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

  • Potentially malicious external URL detected (high risk: 0.70). The skill configures a remote MCP server endpoint (mcp.deepwiki.com) as a runtime operational dependency for agent functionality, but lacks strong first-party provenance.

Issues (2)

W011
MEDIUM

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

W012
MEDIUM

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

Audit Metadata
Risk Level
MEDIUM
Analyzed
Oct 30, 2026, 09:43 PM
Issues
2