git-worktrees

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands and git operations (git worktree, git check-ignore) to create and manage workspaces across POSIX and PowerShell environments.
  • [COMMAND_EXECUTION]: The skill automatically executes setup and test scripts found within the repository to establish a project baseline, which constitutes dynamic execution of local code.
  • [EXTERNAL_DOWNLOADS]: The skill triggers external package managers (npm, pip, cargo, go) to download and install dependencies based on configuration files (package.json, requirements.txt, etc.) detected in the repository.
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by ingesting and following guidance from untrusted repository files like README.md or CLAUDE.md.
  • Ingestion points: Reads repository documentation and configuration files as specified in SKILL.md.
  • Boundary markers: No explicit delimiters or instructions are used to distinguish trusted instructions from untrusted file content.
  • Capability inventory: Capable of executing shell commands and running arbitrary scripts via references/posix.md and references/powershell.md.
  • Sanitization: No sanitization or validation of the content read from the repository files is performed.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 08:26 PM
Security Audit — agent-trust-hub — git-worktrees