netdata-mcp-integration

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a configuration guide for the Netdata MCP integration. All referenced tools, binaries (such as the nd-mcp bridge), and network endpoints (e.g., app.netdata.cloud) are official resources belonging to the vendor.
  • [CREDENTIALS_UNSAFE]: The instructions describe how users can retrieve their own MCP API keys from local filesystem paths like /var/lib/netdata/mcp_dev_preview_api_key. All configuration examples use placeholders such as YOUR_API_KEY or environment variables, adhering to safe credential management practices.
  • [COMMAND_EXECUTION]: The skill provides examples of administrative commands (e.g., claude mcp add, curl) used to configure or verify the connection. These are intended for user execution during setup. The documentation for the execute_function tool correctly identifies it as side-effecting and explicitly advises users to confirm its safety before approving calls.
  • [PROMPT_INJECTION]: No malicious patterns, safety bypasses, or instructions to override agent behavior were detected. The content is strictly technical and instructional.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 11:23 AM
Security Audit — agent-trust-hub — netdata-mcp-integration