using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard development commands including git worktree, npm install, cargo build, pip install, poetry install, and various test runners based on project file detection.
  • [EXTERNAL_DOWNLOADS]: The skill triggers the download and installation of project dependencies from official package registries (e.g., NPM, PyPI, Cargo) during environment setup.
  • [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection (Category 8) by processing contents of CLAUDE.md and repository setup files. Ingestion points: CLAUDE.md, package.json, Cargo.toml, requirements.txt, pyproject.toml, go.mod. Boundary markers: None. Capability inventory: Shell execution of git and package manager commands. Sanitization: None detected.
  • [DATA_EXFILTRATION]: The skill may access the ~/.config/superpowers/ directory in the user's home path if the user selects the global worktree storage option.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 10:40 AM
Security Audit — agent-trust-hub — using-git-worktrees