Tag

#browser-security

38 stories taggedbrowser-security · page 3 of 3.

AI Security

Context Manipulation Attack 'BioShocking' Turns Agentic Browsers Into Credential Thieves

Researchers show how poisoned context fed to AI-driven browser agents causes them to drop safety guardrails and quietly exfiltrate stored credentials.

3 min read
AI Security

DeepSeek-Generated PoC Ransomware Runs Entirely in the Browser via Chromium File System Access API

Researchers documented what they describe as the first frontier-model-produced malware artifact that fuses LLM ideation with a legitimate Chromium capability to encrypt user files without dropping a single native binary.

3 min read
AI Security

DeepSeek Spits Out Working Browser-Native Ransomware for Windows and Android

Researchers say a frontier model stitched together a real Chromium capability with discarded malware concepts and produced something that actually encrypts files from inside a tab.

3 min read
AI Security

Malicious Extension Spoofs AI Platform to Intercept Searches

A fake Perplexity AI browser extension routed search queries through attacker-controlled servers. It's a visibility problem enterprises haven't solved.

3 min read
AI Security

BioShocking: Prompt-Game Trick Pries Credentials From AI Browsers

Researchers at LayerX got six AI browsers and assistants, including ChatGPT Atlas, Perplexity's Comet and Anthropic's Claude extension, to exfiltrate user logins by framing the attack as a game.

3 min read
Threat Intelligence

Fake Perplexity Extension Siphoned Every Chrome Address Bar Keystroke

Microsoft researchers flagged a counterfeit Perplexity Chrome extension that routed queries and omnibox input through an attacker server before completing the search.

3 min read
Threat Intelligence

Featured Chrome Ad Blocker with 10M+ Installs Carries Dormant JS Injection Capability

Researchers flagged a Featured-badge extension that can pull and execute remote JavaScript, a capability common to supply-chain abuse clusters tracked across the Chrome Web Store.

3 min read
AI Security

AutoJack: When the AI Browser Becomes the Initial Access Broker

Microsoft researchers describe an exploit chain that turns an agentic browser into a one-click path from web page to host process execution.

3 min read
© 2026 Threat Vectr