using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Apr 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands for repository management (git worktree add, git commit), project initialization (npm install, pip install, poetry install, go mod download, cargo build), and test verification (npm test, pytest, cargo test, go test). These commands are essential for the skill's purpose and follow a logical, user-controlled workflow.\n- [EXTERNAL_DOWNLOADS]: Dependencies are fetched from standard public registries via official package managers when a worktree is initialized. No downloads from unknown or untrusted third-party sources were identified.\n- [PROMPT_INJECTION]: The skill ingests data from local project files, which constitutes a standard indirect prompt injection surface for development tools.\n
  • Ingestion points: Reads CLAUDE.md for directory preferences and identifies project types via package.json, Cargo.toml, requirements.txt, pyproject.toml, and go.mod.\n
  • Boundary markers: No specific delimiters or boundary markers are employed to isolate untrusted project data from instructions.\n
  • Capability inventory: The skill possesses capabilities to write to the file system (modifying .gitignore) and execute shell commands through multiple language-specific ecosystems.\n
  • Sanitization: No sanitization or validation logic is applied to the content of the project files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 6, 2026, 05:54 PM
Security Audit — agent-trust-hub — using-git-worktrees