Find notable cyber news and cases, enriched with sources, timelines, and signals.

AI Sidebar Spoofing against Atlas and Comet

Technical Analysis
First reported
Last updated
Happening score
H score 16
1 unique sources, 1 articles

Summary

Hide ▲

Researchers demonstrated AI Sidebar Spoofing against OpenAI Atlas and Perplexity Comet, showing that a fake sidebar overlay can steer users toward phishing, OAuth abuse, and even a reverse shell command. The attack matters because it exploits the browser’s trusted AI interface rather than a server-side flaw. It turns a browser extension plus injected JavaScript into a high-risk social-engineering channel.

Related Happenings

Versa Networks launches Secure Enterprise Browser to extend SASE policies into the browser workspace

Security Tool/Service
First: 22.05.2026 18:43 Last: 22.05.2026 18:43 Sources 1

About this happening: Versa Networks **released** a **Secure Enterprise Browser** that extends **SASE policies** directly into the **browser workspace**, giving the company a browser-level control poin...

Chromium JavaScript background RCE flaw

Vulnerability
First: 21.05.2026 21:13 Last: 21.05.2026 21:13 Sources 1

About this happening: The unfixed **Chromium** flaw keeps **JavaScript** running after the browser is closed, creating **remote code execution** risk across **Chromium-based browsers**. A malicious sit...

108 Malicious Google Chrome extensions sharing a C2 backend

Malware Activity
First: 14.04.2026 11:35 Last: 14.04.2026 11:35 Sources 1

About this happening: **108 malicious Google Chrome extensions** were found to use the same **C2 infrastructure** to steal credentials, sessions, and browsing data while injecting ads and arbitrary Jav...

ShieldGuard browser-extension data-harvesting malware

Malware Activity
First: 18.03.2026 16:15 Last: 18.03.2026 16:15 Sources 1

About this happening: A malicious **ShieldGuard** browser extension was dismantled after it was found harvesting sensitive data from **crypto users**, putting wallet and account information at risk. Th...

Perplexity Comet prompt-injection research shows agentic browsers can be trained into phishing traps

Technical Analysis
First: 11.03.2026 18:38 Last: 11.03.2026 18:38 Sources 1

About this happening: **Perplexity's Comet AI browser** is the focus of a **technical analysis** thread showing how **prompt injection** and **malicious URLs** can steer an agentic browser into **data...

Timeline

  1. 23.10.2025 17:09 2 articles · 7mo ago

    AI Sidebar Spoofing against Atlas and Comet

    Initial Disclosure

    SquareX first demonstrated that a malicious extension can draw a fake AI sidebar over the real one in **Comet**. The same overlay behavior was then confirmed on **Atlas**, where it can steer users into unsafe actions across sites.

    Show sources