More results...
Impersonating a legitimate extension from AITOPIA, the two malicious extensions were also exfiltrating users’ browser activity.
The post Chrome Extensions With 900,000 Downloads Caught Stealing AI Chats appeared first on SecurityWeek.
Arizona is the latest state to sue Temu and its parent company PDD Holdings over allegations that the Chinese online retailer is stealing customers’ data.
The post Arizona Attorney General Sues Chinese Online Retailer Temu Over Data Theft Claims appear…
The number of Salesforce customers affected by the recent compromise of Gainsight-published applications is yet to be publicly confirmed, but Salesforce released indicators of compromise (IoCs) and simultaneously shed some light on when the attack like…
Security researchers at Cato Networks have uncovered a new indirect prompt injection technique that can force popular AI browsers and assistants to deliver phishing links or disinformation (e.g., incorrect medicine dosage guidance or investment advice)…
In what may be a repeat of the Salesloft Drift supply chain compromise, Salesforce confirmed that they’ve identified unusual activity involving Gainsight-published apps connected to Salesforce. “Our investigation indicates this activity may…
A new infostealer is targeting macOS users by masquerading as the legitimate DynamicLake UI enhancement and productivity utility and possibly Google’s Drive for desktop app. Multi-stage delivery Dubbed DigitStealer by Jamf researchers, this threat is u…
This report examines how employment and recruitment function on the dark web, based on over 2,000 job-related posts collected from shadow forums between January 2023 and June 2025.
Mindgard reveals 4 critical security flaws in the popular Cline Bot AI coding agent. Learn how prompt injection can hijack the tool for API key theft and remote code execution.
PromptLock, the AI-powered proof-of-concept ransomware developed by researchers at NYU Tandon and initially mistaken for an active threat by ESET, is no longer an isolated example: Google’s latest report shows attackers are now creating and deploying o…
An attacker can inject indirect prompts to trick the model into harvesting user data and sending it to the attacker’s account.
The post Claude AI APIs Can Be Abused for Data Exfiltration appeared first on SecurityWeek.