using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands for environment discovery (
ls), configuration extraction (grep), and git workspace management (git worktree). - [EXTERNAL_DOWNLOADS]: The skill automates project setup by invoking package managers (
npm install,pip install,poetry install,go mod download) which fetch third-party dependencies from external registries. - [REMOTE_CODE_EXECUTION]: The skill triggers the execution of project-defined scripts through setup and test commands (
npm test,cargo build,pytest). This allows the repository's configuration to execute arbitrary code, which is a standard development workflow risk. - [PROMPT_INJECTION]: The skill parses
CLAUDE.mdfor user preferences usinggrep. While the extraction is targeted, it allows project-level files to influence the agent's choice of directories.
Audit Metadata