git-worktree-manager

Pass

Audited by Gen Agent Trust Hub on Nov 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill's core functionality relies on executing Git commands and shell scripts. The Python scripts (worktree_manager.py, port_allocator.py, worktree_validator.py) use the subprocess.run module with argument lists to execute Git commands, which is a secure practice that mitigates shell injection risks.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local Git repository, such as branch names and environment variable keys, which could be exploited in an indirect prompt injection attack if the agent is used on a malicious project.
  • Ingestion points: worktree_manager.py parses output from git worktree list, and worktree_validator.py reads keys from .env files.
  • Boundary markers: No specific delimiters or safety warnings are present to distinguish repository-provided data from instructions.
  • Capability inventory: The skill has capabilities to perform file system operations (creation/removal) and command execution via Git.
  • Sanitization: Input strings are used as arguments in list-based subprocess calls, providing basic protection against command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 12, 2026, 07:06 PM