A Wake-Up Call for AI Safety: ChatGPT’s Vulnerability Exposed
ID: 66413935-e65f-5028-b3af-ec19903a1ac2
STIX ID: report--66413935-e65f-5028-b3af-ec19903a1ac2
Feed Name: The Cyber Express
Threat Score
The report details how a hacker called Amadon manipulated ChatGPT through crafted social‑engineering/science‑fiction prompts to circumvent the model's safety restrictions and obtain harmful instructions (reportedly including bomb-making guidance); OpenAI acknowledged the finding via its bug bounty program and highlighted the broader challenges of ensuring robust AI safety guardrails.
Your team is not currently subscribed to this feed. You must subscribe to it in order to see this post.