using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell operations including git worktree, npm install, cargo build, pip install, poetry install, and go test. It also modifies and commits changes to the project's .gitignore file (SKILL.md).\n- [EXTERNAL_DOWNLOADS]: The skill automatically initiates network requests via package managers (npm, pip, poetry, go) to install dependencies when configuration files are detected (SKILL.md).\n- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface due to its configuration discovery logic.\n
  • Ingestion points: Reading directory preference strings from CLAUDE.md using grep (SKILL.md).\n
  • Boundary markers: There are no delimiters or instructions to ignore instructions found within CLAUDE.md (SKILL.md).\n
  • Capability inventory: The skill can execute shell commands, write to the file system, and access the network via build tools (SKILL.md).\n
  • Sanitization: The skill lacks validation or sanitization of the strings retrieved from CLAUDE.md before they are used in path construction for shell execution (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 01:15 AM