deploy-cookbook

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill makes extensive use of shell commands to manage the deployment lifecycle. This includes package installation (npm install), authentication (cargo-ai login), project initialization (cargo-ai cdk init), and deployment (cargo-ai cdk deploy).
  • [EXTERNAL_DOWNLOADS]: The skill fetches external resources, including the @cargo-ai/cli Node.js package and cookbook templates from the getcargohq/cargo-cookbooks GitHub repository. These resources are managed by the skill's author.
  • [CREDENTIALS_UNSAFE]: The instructions detail the process for authenticating with the Cargo AI service using email-based codes. Importantly, the skill includes a safety directive to manage secrets via .env files and explicitly forbids the agent from reading, printing, or echoing these sensitive values.
  • [DATA_EXPOSURE]: The skill performs a check on the local filesystem at ~/.claude/plugins/installed_plugins.json to determine if installation tracking should be skipped. It also records installation metadata (slug and session ID) via an API call to the vendor's workspace management service.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 07:44 AM
Security Audit — agent-trust-hub — deploy-cookbook