|
Article: ChatGPT blindly trusts browser content, turning the page into a payload - published 5 months ago. Content: EXCLUSIVE ChatGPT can’t tell its own generated content from attacker-controlled Markdown pulled from external sources, according to a researcher who found the prompt injection technique and reported it to OpenAI. This means that if a user asks the chatbot to summarize a web page that contains hidden instructions, the page can become the payload. An attacker... https://www.theregister.com/research/2026/05/29/chatgpt-prompt-injection-turns-web-pages-into-phishing-lures/5248137 Published: 2026 05 29 12:00:00 Received: 2026 06 09 15:27:22 Feed: The Register - Security Source: The Register - Security Category: Cyber Security Topic: Cyber Security |
|
Article: CISA Adds One Known Exploited Vulnerability to Catalog - published 5 months ago. Content: https://www.cisa.gov/news-events/alerts/2026/05/29/cisa-adds-one-known-exploited-vulnerability-catalog Published: 2026 05 29 12:00:00 Received: 2026 06 09 15:04:48 Feed: CISA Current Activity Source: Cybersecurity and Infrastructure Security Agency (CISA) Category: News Topic: Cyber Security |
|
|
Article: ChatGPT blindly trusts browser content, turning the page into a payload - published 5 months ago. Content: EXCLUSIVE ChatGPT can’t tell its own generated content from attacker-controlled Markdown pulled from external sources, according to a researcher who found the prompt injection technique and reported it to OpenAI. This means that if a user asks the chatbot to summarize a web page that contains hidden instructions, the page can become the payload. An attacker... https://www.theregister.com/research/2026/05/29/chatgpt-prompt-injection-turns-web-pages-into-phishing-lures/5248137 Published: 2026 05 29 12:00:00 Received: 2026 06 09 15:01:13 Feed: The Register - Security Source: The Register Category: News Topic: Cyber Security |
|
Click to Open Code Editor