using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses git utility commands to inspect repository metadata, detect submodules, and manage worktree lifecycles. These operations are restricted to the local filesystem and the repository structure.
  • [COMMAND_EXECUTION]: Automates project setup and validation by conditionally executing standard package managers (npm, cargo, pip, poetry, go) and test runners based on detected configuration files. These actions are standard for development workflows and include a safety fallback for sandbox environments.
  • [PROMPT_INJECTION]: Contains strict procedural instructions (labeled as "CORE PRINCIPLES" and "RED LINES") designed to ensure the agent follows the isolation logic and respects environment constraints. These instructions act as task-specific constraints rather than attempts to bypass platform safety filters.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 06:31 PM
Security Audit — agent-trust-hub — using-git-worktrees