using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill automates project setup by running package managers such as npm, pip, poetry, cargo, and go. These tools fetch external dependencies from their respective public registries based on the project's configuration files.\n- [COMMAND_EXECUTION]: Shell commands are utilized to interact with the Git CLI (e.g., git worktree, git rev-parse) and to execute build and test suites (e.g., npm test, cargo build) to ensure a clean workspace baseline.\n- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through maliciously crafted repository files which could lead to unintended command execution during the setup or testing phases.\n
- Ingestion points: Reads project-level files including package.json, Cargo.toml, requirements.txt, pyproject.toml, and go.mod from the skill's working directory.\n
- Boundary markers: None; the skill executes setup logic automatically based on the presence of these files.\n
- Capability inventory: Includes capabilities for package installation, project building, and test execution via subprocess calls.\n
- Sanitization: No specific sanitization or validation of the repository-provided configuration files is performed prior to execution.
Audit Metadata