NYC

MCP Integration

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 explicitly connects to external MCP servers using SSE/HTTP/WS and stdio with arbitrary URLs and tokens (e.g., "url": "https://api.example.com/mcp", SSE examples, and stdio servers) and its agents are described as querying and analyzing those MCP-provided results (Pattern 2), so it will ingest and interpret untrusted third-party content from public services.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:23 PM