THREAT OPS › Threat News › ChatGPT Lockdown Mode Bypass: Phishing, Malware Delivery, and Silent Data Exfiltration
ChatGPT Lockdown Mode Bypass: Phishing, Malware Delivery, and Silent Data Exfiltration
<p class="wp-block-paragraph">Research by: <strong>Alexey Bukhteyev</strong></p>
<h1 class="wp-block-heading">Key Takeaways</h1>
<ul class="wp-block-list"> <li>OpenAI recently introduced Lockdown Mode, an optional advanced security setting designed to protect sensitive user data from prompt injection-based exfiltration attacks.</li>
<li>Check Point Research discovered a vulnerability that
MITRE ATT&CK techniques
Indicators of compromise
- https://openai.com/index/introducing-lockdown-mode-and-elevated-risk-labels-in-chatgpt/url
- https://openai.com/index/ai-agent-link-safety/url
- https://evilwebsite.com/?q=personal_dataurl
- https://evilwebsite.com/malware.exeurl
- https://evilwebsite.com/url
- chatgpt.comdomain