using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes various shell commands to create Git worktrees, manage directory structures, and run development tools (git, npm, cargo, pip, poetry, go).
  • [EXTERNAL_DOWNLOADS]: The skill automatically invokes package managers (npm install, pip install, go mod download) which fetch third-party packages from external registries when specific project files like package.json or requirements.txt are detected.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests data from local project files and executes logic based on their contents. Ingestion points: Reads project configuration files (package.json, Cargo.toml, requirements.txt, pyproject.toml, go.mod) and CLAUDE.md. Boundary markers: None identified. Capability inventory: Includes git worktree management, package installation commands, and test execution (npm test, cargo test, pytest, go test) in SKILL.md. Sanitization: None identified; the skill assumes that project configuration files and the associated test suites are safe to execute without additional validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 05:57 PM