cargo-mcp

Pass

Audited by Gen Agent Trust Hub on Aug 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill documents how to interface with a hosted MCP server at https://mcp.getcargo.io/mcp. This is the official endpoint for the skill's author, getcargohq.
  • [EXTERNAL_DOWNLOADS]: The skill installs the @cargo-ai/cli package via npm. This is a vendor-owned package and follows the expected workflow for this toolset.
  • [COMMAND_EXECUTION]: Contains standard CLI commands for logging in and interacting with the Cargo platform (e.g., cargo-ai login, cargo-ai whoami). These are documented as necessary setup steps for the service.
  • [CREDENTIALS_UNSAFE]: The documentation correctly advises users to manage sensitive API tokens using environment variables (${CARGO_API_TOKEN}) rather than hardcoding them into configuration files, following security best practices.
  • [REMOTE_CODE_EXECUTION]: While it provides commands to add an MCP server via URL, this is a native feature of the MCP protocol and targets the vendor's own infrastructure.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 28, 2026, 05:37 PM
Security Audit — agent-trust-hub — cargo-mcp