using-git-worktrees

Pass

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands to interact with the Git version control system to manage workspace state.
  • Evidence: Step 0 and Step 3 involve running git worktree list --porcelain and git worktree add to inspect and modify the repository structure.
  • [DYNAMIC_EXECUTION]: The skill instructions allow for the execution of project-specific build tools and setup scripts as part of the environment baseline.
  • Evidence: Step 4 mentions running npm install, cargo build, pip install, and other package managers when explicitly required by project documentation.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted documentation and policy files from the repository to determine its behavior.
  • Ingestion points: Step 0 and Step 4 instructions require reading AGENTS.md, CLAUDE.md, lockfiles, and repository setup documentation.
  • Boundary markers: The skill does not define specific delimiters or "ignore instructions" markers for the content read from these files.
  • Capability inventory: The skill has the ability to execute shell commands (git) and build tools (npm, cargo, etc.) based on policies found in the ingested files.
  • Sanitization: No explicit sanitization or validation of the content read from the project files is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 21, 2026, 01:38 AM
Security Audit — agent-trust-hub — using-git-worktrees