# ai-insecure-output-handling

> Exploit apps that trust LLM output — pass model text unsanitized into XSS sinks, SQL, shell, code, or downstream calls. Load when LLM output is rendered as HTML/markdown, executed, or fed to another system. Signals: chatbot output shown with innerHTML/dangerouslySetInnerHTML, "run this code", LLM-ge

Навык · Бесплатно · Лицензия: MIT · Версия: 2026.10.14-ee0e0c5

Установка через CLI NotHoly: `notholy skills install noorqureshi/ai-insecure-output-handling`

Canonical: https://notholy.com/ru/skills/noorqureshi/ai-insecure-output-handling
