skills/kortix-ai/suna/worktree/Gen Agent Trust Hub

worktree

Pass

Audited by Gen Agent Trust Hub on Jul 30, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform various shell operations using pnpm, git, gh, and stripe to create, manage, and tear down development environments.
  • [EXTERNAL_DOWNLOADS]: The CLI tool can automatically install missing development dependencies (like Bun, Node.js, and pnpm) when invoked with the --yes flag. It also utilizes Cloudflare tunnels (*.trycloudflare.com) to allow external services to interact with local development servers.
  • [CREDENTIALS_UNSAFE]: The documentation mentions the use of sensitive keys like STRIPE_SECRET_KEY and requires authenticated CLI sessions. It correctly instructs the agent to ensure these are stored in local .env files rather than being hardcoded.
  • [PROMPT_INJECTION]: The skill includes behavioral guidelines for the agent, such as enforcing the use of worktrees for significant changes and requiring user confirmation before starting new environments.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 30, 2026, 11:48 AM
Security Audit — agent-trust-hub — worktree