The Agent Skills Directory

[SAFE]: No security issues detected. The skill serves as a guide and template provider for prompt engineering tasks. It does not utilize shell tools, perform network requests, or access sensitive files.
[PROMPT_INJECTION]: The skill is designed to ingest and process user-provided prompts. While this represents a surface for indirect prompt injection (Category 8), the risk is negligible because the skill does not have any executable capabilities (such as filesystem or network access) that an injected instruction could exploit. It only generates text-based prompt variants and evaluation rubrics.

prompt-lab