kerng

Posts

• Security Advisory: Anthropic's Slack MCP Server Vulnerable to Data Exfiltration
  by kerngon 6/25/2025, 3:16 AMwith 0 comments
• Hosting COM Servers with an MCP Server (AI-Powered Office Automation)
  by kerngon 6/9/2025, 6:50 AMwith 0 comments
• AI ClickFix: Hijacking Computer-Use Agents
  by kerngon 5/25/2025, 2:02 AMwith 0 comments
• ChatGPT: Dump all your memories and chat history for inspection
  by kerngon 5/8/2025, 1:04 PMwith 0 comments
• Latest Gemini models now follow invisible Unicode Tag instructions
  by kerngon 5/3/2025, 8:20 PMwith 0 comments
• Sneaky Bits: Advanced Data Smuggling using just two invisible Unicode characters
  by kerngon 3/18/2025, 5:18 AMwith 0 comments
• ChatGPT Operator: Prompt Injection Exploits and Defenses
  by kerngon 2/17/2025, 7:50 PMwith 0 comments
• Security ProbLLMs in XAI's Grok: A Deep Dive
  by kerngon 12/23/2024, 6:46 PMwith 0 comments
• How to Find XSS in 2024
  by kerngon 12/1/2024, 3:05 AMwith 0 comments
• Spyware Injection into ChatGPT's Long-Term Memory (SpAIware)
  by kerngon 9/21/2024, 3:54 AMwith 0 comments
• Microsoft Copilot: Prompt Injection, ASCII Smuggling and Exfiltration of Emails
  by kerngon 8/29/2024, 2:56 AMwith 0 comments
• Google Colab AI: Data Leakage Fixed. Some Risks Remain
  by kerngon 7/26/2024, 5:14 AMwith 0 comments
• Breaking Instruction Hierarchy in OpenAI's GPT-4o-mini
  by kerngon 7/23/2024, 3:02 AMwith 0 comments
• Prompt Injections in the Wild – Exploiting LLM Agents – Hitcon 2023 [video]
  by kerngon 7/5/2024, 2:34 PMwith 0 comments
• GitHub Copilot: From Prompt Injection to Data Exfiltration
  by kerngon 6/15/2024, 8:44 PMwith 0 comments
• Automatic Tool Invocation When Browsing with ChatGPT – Threats and Mitigations
  by kerngon 5/29/2024, 5:11 AMwith 0 comments
• Bobby Tables but with LLMs – Google NotebookML Data Exfiltration
  by kerngon 4/16/2024, 3:52 AMwith 0 comments
• ASCII Smuggler: Crafting and Decoding Invisible Text Using Unicode Tags
  by kerngon 1/15/2024, 1:32 PMwith 1 comments
• Prompt Injection exploit in Google Bard leads to data exfiltration
  by kerngon 11/3/2023, 8:45 PMwith 0 comments
• Analyze an image with ChatGPT and have your chat history stolen
  by kerngon 10/14/2023, 1:08 AMwith 0 comments
• ChatGPT Browsing Prompt Injection to Chat History Exfiltration
  by kerngon 10/4/2023, 4:38 AMwith 0 comments
• With AI, Hackers Can Simply Talk Computers into Misbehaving
  by kerngon 8/11/2023, 4:07 AMwith 1 comments
• Image Based Prompt Injections (Bard and Bing Chat)
  by kerngon 7/19/2023, 4:49 AMwith 0 comments
• Google Bard: Image to Prompt Injection
  by kerngon 7/14/2023, 2:24 AMwith 2 comments
• Google Docs AI Features: Vulnerabilities and Risks
  by kerngon 7/13/2023, 12:30 AMwith 0 comments