using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Apr 11, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute standard development commands, including git worktree, npm install, cargo build, and pip install. These are used for workspace initialization and dependency management based on the project's configuration files.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by reading repository-local files such as CLAUDE.md, package.json, and requirements.txt to determine setup steps and configurations.
  • Ingestion points: CLAUDE.md, package.json, requirements.txt, pyproject.toml, go.mod, Cargo.toml.
  • Boundary markers: Absent.
  • Capability inventory: File system modification (.gitignore), git commits, package installation, and test execution.
  • Sanitization: Absent; the skill relies on the agent's interpretation of standard configuration files.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 11, 2026, 09:16 AM