skills/obra/clank/Using Git Worktrees/Gen Agent Trust Hub

Using Git Worktrees

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes standard development commands including git worktree, npm install, pip install, poetry install, go mod download, and various test runners (npm test, pytest, etc.). These operations are consistent with the skill's stated purpose of setting up and verifying development workspaces.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an ingestion surface for indirect prompt injection by reading configuration preferences from local files.
  • Ingestion points: Reading preferences from CLAUDE.md and checking the contents of .gitignore and dependency manifests.
  • Boundary markers: None identified for the file reading operations.
  • Capability inventory: The skill can execute shell commands for package installation and testing across multiple languages (Node.js, Python, Rust, Go).
  • Sanitization: No specific sanitization or escaping of the content read from files is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 06:18 PM