The Agent Skills Directory

COMMAND_EXECUTION (LOW): The skill executes local git commands (git rev-parse, git diff) to determine the scope of files to be processed. It also suggests running project-specific verification commands (lint, tests, typecheck). These are standard operations for a development-focused AI agent.
PROMPT_INJECTION (LOW): As the skill ingests and processes untrusted code files (Category 8), it is technically vulnerable to indirect prompt injection if a source file contains malicious instructions. However, the skill's logic focuses on structural code changes and verification, which provides some natural resistance to instruction-based overrides.
DATA_EXPOSURE (SAFE): The skill reads local file content to perform its primary function. There are no patterns suggesting data is sent to external or untrusted domains.

code-simplify