| Microsoft Copilot: From Prompt Injection to Exfiltration of Personal Information |
|
|
|
| Google AI Studio: LLM-Powered Data Exfiltration Hits Again! Quickly Fixed. |
|
|
|
| CSWSH Meets LLM Chatbots |
|
|
|
| Jailbreak of Meta AI (Llama -3.1) revealing configuration details |
|
|
|
| Zeroday on Github Copilot |
|
|
|
| Shelltorch Explained: Multiple Vulnerabilities in Pytorch Model Server (Torchserve) (CVSS 9.9, CVSS 9.8) Walkthrough |
|
|
|
| Sorry, ChatGPT Is Under Maintenance: Persistent Denial of Service through Prompt Injection and Memory Attacks |
|
|
|
| When Prompts Go Rogue: Analyzing a Prompt Injection Code Execution in Vanna.AI |
|
|
|
| GitHub Copilot Chat: From Prompt Injection to Data Exfiltration |
|
|
|
| Dumping a Database with an AI Chatbot |
|
|
|
| My LLM Bug Bounty Journey on Hugging Face Hub via Protect AI |
|
|
|
| LLM Pentest: Leveraging Agent Integration For RCE |
|
|
|
| Google AI Studio Data Exfiltration via Prompt Injection - Possible Regression and Fix |
|
|
|
| From ChatBot To SpyBot: ChatGPT Post Exploitation |
|
|
|
| Security Flaws within ChatGPT Ecosystem Allowed Access to Accounts On Third-Party Websites and Sensitive Data |
|
|
|
| New Google Gemini Vulnerability Enabling Profound Misuse |
|
|
|
| We Hacked Google A.I. for $50,000 |
|
|
|
| XSS Marks the Spot: Digging Up Vulnerabilities in ChatGPT |
|
|
|
| ChatGPT Account Takeover - Wildcard Web Cache Deception |
|
|
|
| Bypass instructions to manipulate Google Bard AI (Conversational generative AI chatbot) to reveal its security vulnerability i.e. configuration file details exposure |
|
|
|
| AWS Fixes Data Exfiltration Attack Angle in Amazon Q for Business |
|
|
|
| Hacking Google Bard - From Prompt Injection to Data Exfiltration |
|
|
|
| OpenAI Allowed “Unlimited” Credit on New Accounts |
|
|
|
| Shockwave Identifies Web Cache Deception and Account Takeover Vulnerability affecting OpenAI's ChatGPT |
|
|
|
writeups.xyz
/
LLM