using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell command execution to manage Git operations and project environment setup.
  • Evidence: Uses git rev-parse, git branch, and git worktree for workspace management.
  • Evidence: Executes language-specific build and dependency tools: npm install, cargo build, pip install, poetry install, and go mod download based on detected project files.
  • Evidence: Runs verification tests using npm test, cargo test, pytest, and go test ./....
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface as it processes external repository configuration files which could contain malicious directives.
  • Ingestion points: Reads and reacts to the presence of project configuration files like package.json or Cargo.toml in the working directory (SKILL.md, Step 2).
  • Boundary markers: No explicit boundaries or instructions to ignore embedded malicious content are used when processing these files.
  • Capability inventory: Includes filesystem modification (.gitignore), network operations (via package managers), and shell command execution (via build and test tools).
  • Sanitization: No sanitization or validation is performed on the contents of the detected configuration files or the scripts they define before execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 07:07 PM
Security Audit — agent-trust-hub — using-git-worktrees