using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute multiple system commands for environment setup and verification. Specifically, it runs package managers (npm, pip, poetry, cargo, go) and test runners (pytest, npm test) based on the presence of specific configuration files in the workspace. These commands are necessary for the skill's primary purpose of workspace isolation and setup.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project configuration files to drive execution logic, creating a vulnerability surface where malicious file content could influence agent actions.
- Ingestion points: Reads configuration from
package.json,Cargo.toml,requirements.txt,pyproject.toml, andgo.mod(specified inSKILL.mdStep 2). - Boundary markers: None identified. The skill directly executes installation and build commands based on the presence of these files.
- Capability inventory: Includes subprocess execution for package installation (
npm install,cargo build,pip install,poetry install,go mod download) and test execution (npm test,cargo test,pytest,go test). - Sanitization: None identified. The skill proceeds with execution once the configuration file is detected.
Audit Metadata