The Agent Skills Directory

General Security (SAFE): The skill consists solely of markdown instructions for the AI agent to follow when formatting text. No scripts, executable code, or environment modifications are present.
Indirect Prompt Injection (LOW): The skill instructs the agent to read output from git diff --staged. While this constitutes an ingestion point for potentially untrusted data (code changes), the skill does not possess any exploitable capabilities such as network access or file writing, rendering the risk negligible.
External Links (SAFE): The link provided (gitmoji.dev) is a standard documentation resource and is used for human/agent reference only, not for automated downloads or execution.

git-commit