using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes various shell commands for directory management, Git operations (worktree creation), and automated setup tasks. It triggers the execution of build and test tools like 'npm install', 'cargo build', and 'pytest', which run code defined within the repository.\n- [EXTERNAL_DOWNLOADS]: The skill uses standard package managers (npm, pip, poetry, go, cargo) to download project dependencies from public registries based on configuration files found in the project.\n- [PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection. 1. Ingestion points: Reads 'CLAUDE.md' and various project manifest files to determine configuration and setup logic. 2. Boundary markers: None; instructions extracted from these files are followed without isolation. 3. Capability inventory: Execution of arbitrary build and test commands. 4. Sanitization: No validation or sanitization of the repository-provided configuration is performed before execution.
Audit Metadata