using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill automatically executes environment setup and testing commands (npm install, pip install, cargo build, pytest, etc.) upon detecting corresponding configuration files in the repository. While expected for its purpose, this behavior allows for the execution of code defined within the repository's build scripts.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection by processing untrusted data to control execution flow and command arguments.
  • Ingestion points: The skill reads directory preferences from CLAUDE.md in the repository root and incorporates project names and branch names into shell commands.
  • Boundary markers: Absent; the skill directly searches for and potentially acts on string matches within CLAUDE.md and interpolates branch names into command strings without delimiters.
  • Capability inventory: Extensive shell execution capabilities including git, npm, cargo, pip, poetry, and go.
  • Sanitization: No explicit sanitization or validation of the input retrieved from project files, project names, or branch names before they are used in shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:54 AM
Security Audit — agent-trust-hub — using-git-worktrees