using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Oct 1, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses standard package managers (
npm,pip,cargo,go) to download project dependencies from well-known official registries. - [COMMAND_EXECUTION]: The skill executes shell commands for git operations (
git worktree add,git branch), file system checks (ls,cd), and environment setup tasks (npm install,cargo build, etc.). - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted local project files to decide which installation and test commands to execute. Maliciously crafted configuration files (e.g.,
package.jsonwith pre-install scripts) could lead to unintended code execution when the skill is invoked. - Ingestion points: Local project files such as
package.json,Cargo.toml,requirements.txt,pyproject.toml, andgo.mod(found in SKILL.md). - Boundary markers: The skill does not use specific delimiters or instructions to ignore potential malicious content within these files.
- Capability inventory: Shell execution for package installation, project building, and test execution across multiple languages (SKILL.md).
- Sanitization: No validation or sanitization of the configuration file contents is performed before they are passed to the underlying tools.
Audit Metadata