using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple shell commands to manage Git worktrees and project environments. This includes git operations (rev-parse, worktree, branch), dependency management (npm, cargo, pip, poetry, go), and testing suites (pytest, go test).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project configuration files which creates an attack surface for malicious repository content.
  • Ingestion points: Local repository files including package.json, Cargo.toml, requirements.txt, pyproject.toml, and go.mod.
  • Boundary markers: None present; the skill treats project files as authoritative.
  • Capability inventory: Full subprocess execution for Git and various language-specific build tools across the file system.
  • Sanitization: None; the skill executes commands defined or implied by the project files.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 12:44 AM