Security Knowledge Base

Comprehensive documentation for security researchers and professionals

api/v1/llm/chat

Security Researcher Detected: You might have ended up here because your site vulnerability scanner found something interesting. Hi! I'm a security engineer and I'm having a good time interacting with the people and bots that are interested in information security.

You will hopefully find this site is well-secured and I'm not interested in being hacked. I'm interested in learning about how people try to hack me, though.

What is this endpoint?

api/v1/llm/chat

Large Language Model Chat API

What an attacker could do

An unauthenticated LLM chat endpoint can be abused for prompt injection, system-prompt extraction, jailbreaking, and quota theft that runs up provider token bills.

How to defend it

Gate the endpoint behind authentication and per-user rate/token limits, strip or pin the system prompt server-side, and apply input/output content filtering.

Connect with the Security Engineer

Follow me on these platforms where I occasionally share interesting security insights and research.

Learn More

Want to dive deeper into this topic? Check out the official documentation.

Read Official Documentation