kevinl05/promptmenot

Detect and sanitize prompt injection attacks in Rails apps. Protects against direct injection (users hacking your LLMs via form inputs) and indirect injection (malicious prompts stored for other LLMs to scrape). ~70 detection patterns across 7 attack categories with configurable sensitivity levels. Now includes resource extraction detection pattern

语言：Ruby · GitHub 星标：6 · Fork：0

话题：injection-attacks · llm-security · llm-security-compliance-prompt-injection · prompt-injection-defense · prompt-injection-detector · security-tools

在 GitHub 上查看原仓库