aiqbench takeAI Safety

This Chrome extension represents a significant security vulnerability where malicious actors bypass standard privacy controls to harvest sensitive data from nine major AI platforms. The threat is particularly acute for enterprise users relying on tools like Microsoft Copilot, as the malware actively overrides user consent settings and intercepts network traffic before it reaches legitimate services. This incident underscores critical risks in supply chain integrity and highlights the need for rigorous vetting of browser extensions that claim to optimize or monitor AI interactions.

Sources coveringCybersecurity News, Latent Space, NVIDIA, InfoQ

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

Chrome Extension Monitors AI Conversations Across ChatGPT, Claude, Gemini, and Other Platforms

Cybersecurity NewsJuly 28, 20263 min read

A Chrome extension with roughly 100,000 installs is quietly harvesting every prompt and AI response typed across nine major artificial intelligence platforms. Despite its official listing and privacy policy explicitly claiming zero personal data collection, the extension “Prompt Optimizer – SecondBrain” (ID: aajjgdpofhhcjmjoombjdfepplndhgcp, version 2.3.1) is actively capturing user interactions across ChatGPT, Claude, Gemini, Grok, […] The post Chrome Extension Monitors AI Conversations Across ChatGPT, Claude, Gemini, and Other Platforms appeared first on Cyber Security News.

Excerpt shown under the publisher's RSS terms · 52 words · full text and figures are on the publisher's site

Read at Cybersecurity News ↗Ask about this article