using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Nov 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through project configuration files that it automatically processes and acts upon.
  • Ingestion points: The skill reads package.json, Cargo.toml, requirements.txt, pyproject.toml, and go.mod from the repository to determine the environment type.
  • Boundary markers: The instructions do not define boundary markers or require the agent to ignore potentially malicious content within these configuration files.
  • Capability inventory: The skill has the capability to execute shell commands including npm install, cargo build, pip install, poetry install, go mod download, and various testing suites (npm test, cargo test, pytest, go test).
  • Sanitization: There is no sanitization or validation of the contents of these files before they are used to trigger execution of external tools.
  • [COMMAND_EXECUTION]: The skill automatically executes powerful shell commands for environment setup and validation.
  • Evidence: The skill executes npm install, cargo build, pip install -r requirements.txt, poetry install, and go mod download in Step 2, followed by test execution in Step 3 (npm test, cargo test, pytest, or go test ./...) based on file detection.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 17, 2026, 03:11 PM