worktree

Warn

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: MEDIUMCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on shell command execution to interact with the Git repository and the local filesystem.
  • Evidence: The SKILL.md file contains several bash script blocks designed to execute git worktree list, git worktree add, and git worktree remove commands.
  • [COMMAND_EXECUTION]: User-provided input is interpolated directly into shell scripts, posing a risk of command injection.
  • Evidence: In the 'Create New Agent Worktree' section, the skill instructions state NAME="" # Set from ARGUMENTS if present. This user-controlled variable is then used to construct the WT_PATH and BRANCH variables, which are passed to the git worktree add "$WT_PATH" -b "$BRANCH" command. If the user input includes shell metacharacters such as backticks, semicolons, or subshell expansions (e.g., $(...)), it could lead to the execution of arbitrary commands within the agent's environment.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 21, 2026, 07:18 AM