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

AI assistants with web browsing repurposed as covert C2 relays

Technical Analysis
First reported
Last updated
Happening score
H score 28
1 unique sources, 1 articles

Summary

Hide ▲

AI assistants with web browsing are now being shown as covert command-and-control relays, letting malware hide commands and stolen data inside routine enterprise traffic. Grok and Microsoft Copilot can be prompted through public web interfaces to fetch attacker-controlled URLs and return responses, effectively acting as a proxy. The technique works without an API key or registered account, raising the risk of stealthy abuse across AI-enabled workflows.

Related Happenings

LayerX font-rendering PoC exposes a browser-rendering gap in AI assistant analysis

Technical Analysis
First: 17.03.2026 15:59 Last: 17.03.2026 15:59 Sources 1

About this happening: A **LayerX** proof-of-concept showed that a **font-rendering attack** can hide malicious webpage commands from AI assistants, creating a risk of **unsafe guidance** when the brows...

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...

Starkiller dark-web phishing platform scales credential theft as a SaaS-style criminal service

Threat Actor Meta
First: 19.02.2026 14:00 Last: 19.02.2026 14:00 Sources 1

About this happening: The **Starkiller** phishing platform has emerged as a **SaaS-style criminal service**, raising the scale and durability of credential theft operations. It is sold on the **dark we...

AI as a C2 proxy abuse of Microsoft Copilot and xAI Grok browsing channels

Technical Analysis
First: 17.02.2026 20:08 Last: 17.02.2026 20:08 Sources 1

About this happening: Researchers disclosed **AI as a C2 proxy**, a technique that can turn **Microsoft Copilot** and **xAI Grok** browsing features into stealthy **command-and-control relays**, increa...

AI Recommendation Poisoning in "Summarize with AI" buttons

Technical Analysis
First: 17.02.2026 11:31 Last: 17.02.2026 11:31 Sources 1

About this happening: **AI Recommendation Poisoning** now shows how clickable **"Summarize with AI"** buttons can inject persistent prompts into chatbot memory, creating a new path to bias recommendati...

Timeline

  1. 18.02.2026 17:00 2 articles · 3mo ago

    AI assistants with web browsing abused as covert C2 relays

    Initial Disclosure

    Check Point Research described a proof-of-concept showing that AI assistants with web browsing, including Grok and Microsoft Copilot, can be manipulated through public web interfaces to fetch attacker-controlled URLs and return responses, turning the AI service into a proxy that relays commands to infected machines and sends stolen data back out without an API key or registered account. The researchers also used a WebView2 browser component inside a C++ program to automate invisible interaction with the interface and showed commands embedded in HTML being parsed and executed.

    Show sources