TLDR
Threat actors use jailbreak prompts (DAN, DUDE, role play 'pretend you are an AI without restrictions') to bypass safety on ChatGPT / Claude / Gemini and request explosive synthesis, malware code, phishing templates, weapon design....
How it works
Threat actors use jailbreak prompts (DAN, DUDE, role play 'pretend you are an AI without restrictions') to bypass safety on ChatGPT / Claude / Gemini and request explosive synthesis, malware code, phishing templates, weapon design....
Red flags
- Urgent pressure to click, pay, or share codes immediately.
- A link or sender that does not match the official organization.
- Requests for card data, passwords, OTPs, wallet signatures, or bank transfers.
What to do
- 1OpenAI's Oct 2024 report disrupted 20+ such operations.
Source
OpenAI-Disclosure
Source reviewed by Mythos Forensic Team
https://openai.com/index/disrupting-malicious-uses-of-our-models/FAQ
Is LLM jailbreak for crime instructions (DAN / DUDE / role play prompt engineering) a real scam pattern?
Yes. Treat the message, call, or payment request as suspicious until you verify it through an official channel.
What are the first warning signs?
Urgent pressure to click, pay, or share codes immediately.; A link or sender that does not match the official organization.; Requests for card data, passwords, OTPs, wallet signatures, or bank transfers.
What should I do first?
OpenAI's Oct 2024 report disrupted 20+ such operations.
Can LegalAudit check my case?
Yes. Start a free chat and paste the message, link, sender, or payment details for triage.