safe-worktree

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFE
Full Analysis
  • COMMAND_EXECUTION (SAFE): The script executes Git and GitHub CLI commands (git, gh) to manage worktrees and branches. These are the primary functions of the skill and include multiple safeguards:
  • Explicitly refuses to delete protected branches ('main', 'master', 'develop', etc.).
  • Validates that the worktree path is not a sensitive system directory like / or $HOME.
  • Verifies that the branch is merged into the integration branch before deletion unless overridden.
  • Includes fallback mechanisms using git update-ref and the GitHub API to ensure deletions are performed even when standard commands are restricted.
  • PROMPT_INJECTION (SAFE): No malicious instructions or bypass attempts were detected in the skill's documentation or metadata.
  • EXTERNAL_DOWNLOADS (SAFE): The skill does not perform any external downloads or package installations during execution.
  • DATA_EXFILTRATION (SAFE): The skill only interacts with local Git repository metadata and the specified GitHub repository to perform cleanup tasks. No sensitive data is transmitted to unauthorized domains.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 11:47 AM