using-git-worktrees
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple shell commands to manage git worktrees, modify the .gitignore file, and perform project setup using standard development tools.
- [INDIRECT_PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection by ingesting and acting upon untrusted data from the repository being processed.
- Ingestion points: The skill reads project configuration files (package.json, Cargo.toml, requirements.txt, pyproject.toml, go.mod) and searches for patterns within CLAUDE.md (via grep).
- Boundary markers: Absent; the skill does not use delimiters or safety instructions when processing these files.
- Capability inventory: The skill can modify the local file system (writing to .gitignore), commit changes to the repository, and execute arbitrary code through package managers during the installation phase.
- Sanitization: Absent; malicious project files could exploit the automatic setup phase to execute arbitrary scripts (e.g., npm preinstall scripts or malicious requirements.txt entries).
Audit Metadata