using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill automatically executes shell commands for dependency installation and test suite execution (e.g., npm install, cargo test, pip install) based on the presence of project manifest files.
  • [PROMPT_INJECTION]: Potential surface for indirect prompt injection via untrusted project data.
  • Ingestion points: The skill reads directory preferences from CLAUDE.md and analyzes project manifest files.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are used when reading CLAUDE.md.
  • Capability inventory: The skill can execute arbitrary shell commands via project-defined scripts and install external packages.
  • Sanitization: Project file contents are not validated or sanitized before being used to trigger automated actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 02:03 AM