Malicious Chrome Extensions Steal ChatGPT and DeepSeek Conversations
Two rogue Chrome extensions, impersonating the legitimate AITOPIA AI sidebar tool, have compromised over 900,000 users by exfiltrating ChatGPT and DeepSeek conversations along with full browsing histories to attacker-controlled servers. The extensions, named "Chat GPT for Chrome with GPT-5, Claude Sonnet & DeepSeek AI" and "AI Sidebar with Deepseek, ChatGPT, Claude and more," request consent for "anonymous analytics" but covertly steal sensitive data, including proprietary code, business strategies, PII, and internal URLs. The malware operates by monitoring browser tabs, scraping chat content and session IDs, and sending Base64-encoded data to C2 servers every 30 minutes, exposing users to risks such as espionage, identity theft, and phishing.
Researchers from OX Security discovered the threat, noting that the extensions remain available on the Chrome Web Store, with one losing its "Featured" badge after disclosure. The extensions also redirect users to each other if uninstalled, and their privacy policies are hosted on third-party sites to obscure their origins. The incident highlights the growing trend of browser extensions being used to capture AI chatbot conversations, a tactic dubbed "Prompt Poaching," and underscores the need for vigilance when installing browser add-ons, especially those requesting broad permissions under the guise of analytics or enhanced user experience.
Get ahead of threats like this
Mallory correlates global threat intelligence with your attack surface — know if you’re exposed before adversaries strike.
How this story unfolded
4 events from the most recent confirmed update back to the earliest known activity.
Google leaves reported malicious extensions available in Chrome Web Store
Despite being reported to Google, the malicious extensions remained available for download as of 2026-01-07, indicating delayed enforcement in the Chrome Web Store. One of the extensions had its 'Featured' badge removed after disclosure, but both were still accessible to users.
Additional scrutiny falls on legitimate extensions collecting AI chat data
By 2026-01-06, reporting also highlighted that legitimate extensions such as Similarweb and Stayfocusd were collecting AI chatbot conversation data, broadening concern beyond outright malicious add-ons. Similarweb was noted as having updated its privacy policy to explicitly reflect this data collection practice.
Researchers report nearly 1 million users exposed by extension data theft
Researchers said the two malicious extensions had amassed more than 900,000 installs, exposing users' private AI chats, authentication tokens, internal URLs, proprietary code, business information, and other sensitive data. The findings highlighted risks including corporate espionage, identity theft, phishing, and intellectual property theft.
OX Security uncovers two malicious AI-themed Chrome extensions
On 2025-12-29, OX Security researchers revealed that two Chrome extensions impersonating the legitimate AITOPIA AI sidebar were stealing ChatGPT and DeepSeek conversations along with browsing data from users. The extensions used DOM scraping and browser APIs to collect sensitive chat content, session data, and browsing history, then exfiltrated it to attacker-controlled servers every 30 minutes.
Related entities
Vulnerabilities, threat actors, malware, products, organizations, and breaches Mallory has linked to this story.
Sources
3 references tracked. Mallory keeps watching after this page renders.
Fake ChatGPT and DeepSeek Extensions Spied on Over 1 Million Chrome Users
hackread.com
Open sourceMalicious Chrome Extension Steal ChatGPT and DeepSeek Conversations from 900K Users
cybersecuritynews.com
Open sourceTwo Chrome Extensions Caught Stealing ChatGPT and DeepSeek Chats from 900,000 Users
thehackernews.com
Open sourceSee the full picture, correlated to your attack surface.
Map indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Related stories
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Malicious Chrome Extensions Stole Conversations From ChatGPT, Claude, Gemini, and DeepSeek
Researchers reported that several AI-themed browser extensions in official marketplaces covertly harvested user conversations from generative AI services including **ChatGPT, Claude, Copilot, Gemini, and DeepSeek**. G Data identified **Urban VPN**, **Smart Sidebar: ChatGPT, Claude and DeepSeek**, and **AI Assistant/Chat AI** as examples that remained outwardly functional while injecting scripts, intercepting requests, tampering with page content, or using hidden iframes to capture prompts and responses from visited AI sites. Investigators said the stolen data included conversation IDs, hostnames, timestamps, and full chat histories, with some payloads encoded in Base64 and sent to external servers. The extensions reportedly had strong ratings, large user bases, and in one case a Chrome Web Store **Featured** badge, underscoring how official store vetting can miss dynamic malicious behavior such as remote iframe communications; researchers warned that AI-focused extensions now expose a broad attack surface and urged enterprises to enforce strict extension allow-listing, minimize permissions, and remove unnecessary add-ons from systems accessing sensitive AI platforms.
Jun 15, 2026
Malicious and High-Risk AI-Powered Chrome Extensions Enable Account Hijacking and Phishing
Security researchers reported multiple risks tied to **AI-themed browser extensions** in the Chrome/Edge ecosystem, including active malicious campaigns. Malwarebytes identified **16 malicious extensions** (15 Chrome, 1 Edge) masquerading as ChatGPT “enhancers” that **steal ChatGPT session tokens**, enabling attackers to take over accounts and access conversation history and metadata; the extensions also exfiltrate additional telemetry (e.g., extension version/language and usage details) to help attackers profile victims and maintain longer-term access. Separately, Varonis described a new **malware-as-a-service** offering called **“Stanley”** that claims to reliably get **phishing-capable Chrome extensions** through Chrome Web Store review, using full-screen `iframe` overlays to present attacker-controlled login pages while the address bar continues to show the legitimate domain; it also advertises auto-install support across Chrome/Edge/Brave, a management panel, geo/IP targeting, and frequent C2 polling. In parallel with these overtly malicious cases, an Incogni study of **442 AI-powered Chrome extensions** found broad privacy and security exposure from over-privileged extensions (e.g., script injection and deep page access) and extensive data collection (52% collecting user data), highlighting that even popular tools (e.g., **Grammarly** and **QuillBot**) can present significant privacy risk due to the scope of permissions and data categories collected.
Mar 21, 2026
Malicious ChatGPT Ad Blocker Chrome Extension Stole User Conversations
Researchers reported that a fake Chrome extension called **"ChatGPT Ad Blocker"** posed as a tool to remove ads from ChatGPT while secretly harvesting users' prompts and responses. The extension reportedly cloned the ChatGPT page DOM, extracted conversation text, and exfiltrated chats longer than 150 characters to a private Discord channel using a bot identified as **Captain Hook**, turning a supposed privacy tool into a straightforward data-theft mechanism. The campaign appears to have capitalized on interest around ChatGPT advertising by luring users with bogus ad-blocking functionality. DomainTools linked the operation to suspicious domains including `blockaiads.com`, `openadblock.com`, and `gptadblock.com`, and found the extension checked a GitHub-hosted file hourly for remote instructions, suggesting active attacker control and the ability to update behavior over time. The developer account was reportedly tied to the handle **`krittinkalra`** and associated with AI platforms Writecream and AI4ChatCo, although no evidence was cited that those other apps also stole data.
Apr 3, 2026