The Problem With the rise of ChatGPT and enterprise LLM integrations, a new attack vector...
The Problem
With the rise of ChatGPT and enterprise LLM integrations, a new attack vector has emerged: Prompt Injection and Jailbreaking. Hackers are actively trying to:
Extract system prompts
Bypass content filters
Steal sensitive data through LLMs
What Is an AI Prompt Injection Attack? The Hidden Threat Hijacking Your Chatbots - Decrypt
ChatGPhish Vulnerability Turns ChatGPT Web Summaries Into a Phishing Surface
ChatGPT blindly trusts browser content, turning the page into a payload
Hackers Are After the Gaps in Your Vulnerability Program: Here's Their Playbook
Scaling malicious code detection from pull requests to the software supply chain | Datadog
Hackers are now using ChatGPT share links to deliver malware
Malicious Notifications Could Trick Google Gemini Users
ChatGPT share links abused to host fake outage pages to deliver malware
This morning, while working on an LLM integration in my own financial analysis tool, I encountered an...
Hackers can hijack ChatGPT, Claude, and Gemini with nothing but a sentence. OpenAI says the problem may never be fully solved.
Will LLMs ever be able to stamp out the root cause of these attacks? Possibly not.
A few months ago I watched someone demo an internal AI assistant during a meeting that had already...
When Text Becomes Code: Securing LLM–Database Integrations When you connect a large...
Unlike most prompt injections, ShadowLeak executes on OpenAI's cloud-based infrastructure.
