Skip to content
Metatext
Sign Up

input-guard

Skillby Kernel8901

Scan untrusted external text (web pages, tweets, search results, API responses) for prompt injection attacks. Returns severity levels and alerts on dangerous content. Use BEFORE processing any text from untrusted sources.

Repository Source folder

Details

Path
人工智能与大型语言模型/input-guard/SKILL.md

FAQ