NYC

git-worktree-workflow

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION] (SAFE): The skill uses standard Git commands (git worktree, git branch, git merge) and calls the claude CLI. These are standard development tools and the usage patterns are confined to local repository management.
  • [REMOTE_CODE_EXECUTION] (SAFE): No remote scripts are downloaded or executed. Code examples provided are documentation-focused and intended for manual or scripted local use by the developer.
  • [DATA_EXFILTRATION] (SAFE): The skill does not access sensitive files (e.g., SSH keys, environment variables) or make any unauthorized network connections.
  • [PROMPT_INJECTION] (LOW): Category 8 (Indirect Prompt Injection) surface is noted because the workflow involves the agent reading and processing code from various branches. This is the primary purpose of the skill and does not represent an inherent security flaw in the instructions themselves.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:15 PM