aiqbench takeAI Safety

This security incident highlights a critical vulnerability in AI privacy where malicious actors exploit legitimate browser extension permissions to harvest sensitive model interactions and subscription data at scale. The operation's use of shared infrastructure across multiple extensions demonstrates an evolved threat landscape specifically targeting the growing ecosystem of generative AI applications, raising urgent concerns about user consent and data sovereignty for both developers and end-users.

Source coveringCybersecurity News

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

PromptSnatcher Ad Blocker Extensions Steal AI Chats From ChatGPT, Claude, and Gemini

Cybersecurity NewsJune 15, 20265 min read

Two browser extensions masquerading as ad blockers have been caught secretly recording private conversations from ChatGPT, Claude, Gemini, and five other major AI platforms. The extensions, named “Smart Adblocker” and “Adblock for Browser,” were installed by roughly 90,000 users before the scheme was uncovered. Users genuinely received ad-blocking functionality while their most sensitive AI conversations […] The post PromptSnatcher Ad Blocker Extensions Steal AI Chats From ChatGPT, Claude, and Gemini appeared first on Cyber Security News.

Two browser extensions masquerading as ad blockers have been caught secretly recording private conversations from ChatGPT, Claude, Gemini, and five other major AI platforms. The extensions, named “Smart Adblocker” and “Adblock for Browser,” were installed by roughly 90,000 users before the scheme was uncovered. Users genuinely received ad-blocking functionality while their most sensitive AI conversations were being quietly siphoned off entirely in the background. The operation, tracked internally as “Panel 231” and named…

Excerpt shown under the publisher's RSS terms · 73 words · full text and figures are on the publisher's site

Read at Cybersecurity News ↗Ask about this article