GPTSafe/PromptGuard
Build production ready apps for GPT using Node.js & TypeScript
Provides prompt injection detection, content/language filtering, token limiting, and caching mechanisms to secure GPT applications against attacks and control costs. Validates inputs through configurable deny lists, built-in attack pattern matching, and token thresholds before queries reach the model. Integrates with OpenAI's token encoding system and exposes a simple async validation API for middleware integration into Node.js/TypeScript applications.
No commits in the last 6 months. Available on npm.
Stars
48
Forks
4
Language
TypeScript
License
Apache-2.0
Category
Last pushed
May 08, 2023
Monthly downloads
32
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/GPTSafe/PromptGuard"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
LouisShark/chatgpt_system_prompt
A collection of GPT system prompts and various prompt injection/leaking knowledge.
CyberAlbSecOP/Awesome_GPT_Super_Prompting
ChatGPT Jailbreaks, GPT Assistants Prompt Leaks, GPTs Prompt Injection, LLM Prompt Security,...
citiususc/smarty-gpt
A wrapper of LLMs that biases its behaviour using prompts and contexts in a transparent manner...
timqian/openprompt.co
Create. Use. Share. ChatGPT prompts
B3o/GPTS-Prompt-Collection
收集GPTS的prompt / Collect the prompt of GPTS