mcp-gateway-configuration

Warn

Audited by Snyk on Mar 4, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 1.00). The skill configures MCP servers that will fetch and consume untrusted public content — e.g., the "playwright" server (navigate/click/screenshot) for browsing web pages, the "github" MCP server (issues/PRs/code search/get_file_contents) for public repository content, and the SSE "remote-server" URL example — which the agent is expected to read and could materially influence its actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 4, 2026, 11:09 PM