using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted metadata files from repositories to automate setup, which could lead to arbitrary code execution if the repository contains malicious configuration.
- Ingestion points: The skill reads project configuration files including package.json, Cargo.toml, requirements.txt, pyproject.toml, and go.mod (SKILL.md).
- Boundary markers: There are no explicit boundary markers or verification steps used to sanitize the contents of these configuration files before they influence execution.
- Capability inventory: The skill executes powerful shell commands such as npm install, cargo build, pip install, poetry install, go mod download, and various test runners (SKILL.md).
- Sanitization: No sanitization or validation of the scripts or dependencies defined in the project files is performed before execution.
- [COMMAND_EXECUTION]: The skill performs multiple shell operations to manage the environment and setup project dependencies.
- It executes git worktree add and git check-ignore to handle workspace isolation and verify ignore status.
- It triggers automated installation and build routines using various package managers based on the presence of specific project files.
Audit Metadata