๐ The finest daily news on cybersecurity and privacy.
๐ Daily releases.
๐ป Is your online life secure?
๐ฉ lalilolalo.dev@gmail.com
Post #90292
139
๐๏ธ AI Recommendation Poisoning: How "Ask AI" Buttons Silently Alter LLM Memory ๐๏ธ
๐ Read more.
๐ Via "The Hacker News"
----------
๐๏ธ Seen on @cibsecurity
A new class of prompt injection is spreading across commercial websites. It requires no malware, no stolen credentials, and no zeroday exploit. It abuses a standard feature built into almost every major AI assistant prefilled deep links. We observed production websites embedding hidden prompt injection payloads inside "Ask AI" buttons on marketing and competitor comparison pages. When a user.๐ Read more.
๐ Via "The Hacker News"
----------
๐๏ธ Seen on @cibsecurity