worktree-ops

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes output from Git commands (such as branch names and worktree paths) and incorporates them into subsequent agent operations without using boundary markers or sanitization logic.\n
  • Ingestion points: Data from git worktree list --porcelain is used to drive the list and removal workflows in SKILL.md.\n
  • Boundary markers: The instructions do not define delimiters (e.g., XML tags) to isolate external data from the agent's core instructions.\n
  • Capability inventory: The skill performs high-privilege operations including branch deletion (git branch -D) and forced worktree removal (git worktree remove --force).\n
  • Sanitization: No validation or escaping is performed on environment-derived variables before they are interpolated into shell commands.\n- [COMMAND_EXECUTION]: Shell commands are constructed by concatenating variables like <name> and <path> directly into Git commands (e.g., git worktree add .worktrees/<name>). This is a potential command injection vector if the input contains shell metacharacters such as semicolons, pipes, or backticks.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 02:46 PM
Security Audit — agent-trust-hub — worktree-ops