using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- COMMAND_EXECUTION (LOW): The skill executes multiple shell commands and package management tools to set up worktrees and prepare environments.
- Evidence: Commands such as
git worktree add,npm install,cargo build,pip install, and various test runners (npm test,pytest) are explicitly defined in the workflow. - Context: While these are intended primary functions for a development-oriented skill, executing these commands on an untrusted repository could trigger malicious scripts (e.g., npm postinstall hooks).
- INDIRECT_PROMPT_INJECTION (LOW): The skill reads from
CLAUDE.mdto determine configuration preferences, creating an ingestion surface for untrusted data. - Ingestion points:
CLAUDE.mdis parsed usinggrepto extract directory preferences. - Boundary markers: Absent; the skill does not use specific delimiters to separate user data from instructions.
- Capability inventory: The skill possesses significant capabilities, including file system writes (
.gitignoremodification), repository modification (git commit), and arbitrary command execution via package managers. - Sanitization: None; the extracted preference is used directly in path construction.
Audit Metadata