using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to interact with Git and manage local directories, including git worktree add, git rev-parse, and git branch.
  • [COMMAND_EXECUTION]: It automatically runs project-level commands like npm install, cargo build, and pytest based on the files found in the repository.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of external packages through standard language-specific package managers when manifest files are detected.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface by processing data from the local repository environment.
  • [PROMPT_INJECTION]: Ingestion points: The skill reads branch names (git branch --show-current) and project names (git rev-parse --show-toplevel) from the shell environment.
  • [PROMPT_INJECTION]: Boundary markers: No delimiters or ignore instructions are provided when handling these strings.
  • [PROMPT_INJECTION]: Capability inventory: The skill has the ability to execute subprocesses through npm, pip, poetry, cargo, and go commands across all supported project scripts.
  • [PROMPT_INJECTION]: Sanitization: There is no evidence of sanitization or escaping for the variables interpolated into shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 09:39 AM
Security Audit — agent-trust-hub — using-git-worktrees