using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: Modifies .gitignore and performs Git commits to ensure local worktree directories remain untracked by the repository.
  • [COMMAND_EXECUTION]: Automates workspace setup by running build, installation, and testing commands (npm, cargo, pip, poetry, go) based on detected project files.
  • [EXTERNAL_DOWNLOADS]: Triggers dependency downloads from official language registries through standard package managers.
  • [PROMPT_INJECTION]: The skill processes external configuration data from CLAUDE.md and project manifests to determine execution logic.
  • Ingestion points: CLAUDE.md, package.json, Cargo.toml, requirements.txt, pyproject.toml, go.mod (found in SKILL.md).
  • Boundary markers: Absent.
  • Capability inventory: Shell command execution for package management and testing across workspace creation steps (found in SKILL.md).
  • Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 11:56 PM
Security Audit — agent-trust-hub — using-git-worktrees