using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with Git (worktree creation, ignore verification), run package manager operations, and execute test suites. These actions are consistent with the primary purpose of providing an isolated development environment.
- [EXTERNAL_DOWNLOADS]: Automates the installation of project-defined dependencies from public package registries using official tools like npm, pip, and cargo.
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by reading from files such as
CLAUDE.mdto determine user preferences. - Ingestion points:
CLAUDE.md(read via grep) and various project configuration files likepackage.jsonorCargo.toml. - Boundary markers: No explicit delimiters are used to wrap data ingested from external files.
- Capability inventory: The skill has the capability to run shell commands, install packages, and execute arbitrary code via test runners.
- Sanitization: No explicit sanitization or input validation is performed on the ingested content before it influences the control flow or is interpolated into commands.
Audit Metadata