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 plugin's unified "mcp" tool makes HTTP/SSE calls to configured MCP server URLs (e.g., POST/GET to /mcp as shown in README.md, API.md and CONFIGURATION.md) and directly parses and displays the returned response.content (e.g., JSON.parse(response.content[0].text)), so agents will ingest and present arbitrary content from external/untrusted MCP servers.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 15, 2026, 08:14 PM