OpenAI recently introduced a new feature for ChatGPT which, unfortunately, also puts users at risk of data exfiltration and persistent access.
In December 2025, a feature called Connectors finally moved out of beta and into general availability. This feature allows ChatGPT to connect to numerous other apps, such as calendars, cloud storage, email accounts, and similar – gaining more context and thus providing users with better, more relevant responses. The feature is now called ‘apps’ but, according to security researchers Radware, also opens up the tool to a major vulnerability – prompt injection attacks.
Read more…
Source: TechRadar News
Sign up for the Cyber Security Review Newsletter
The latest cyber security news and insights delivered right to your inbox
Related:
- An Inside Look into Microsoft Rich Text Format and OLE Exploits
January 24, 2020
There has been a dramatic shift in the platforms targeted by attackers over the past few years. Up until 2016, browsers tended to be the most common attack vector to exploit and infect machines but now Microsoft Office applications are preferred, according to a report published here during March 2019. Increasing use of Microsoft Office as a ...
- Nice Try: 501 (Ransomware) Not Implemented
January 24, 2020
Since January 10, 2020, FireEye has tracked extensive global exploitation of CVE-2019-19781, which continues to impact Citrix ADC and Gateway instances that are unpatched or do not have mitigations applied. We previously reported on attackers’ swift attempts to exploit this vulnerability and the post-compromise deployment of the previously unseen NOTROBIN malware family by one threat actor. FireEye continues to actively track multiple ...
- U.S. Government Agency Targeted With Malware-Laced Emails
January 23, 2020
A U.S. government agency was targeted with spear phishing emails harboring several malware strains – including a never-before-seen malware downloader that researchers call “Carrotball.” The campaign, which researchers observed occurring from July to October and code-named “Fractured Statue,” involved six unique malicious document lures being sent as attachments from four different Russian email addresses to 10 ...
- Shlayer Trojan attacks one in ten macOS users
January 23, 2020
For close to two years now, the Shlayer Trojan has been the most common threat on the macOS platform: in 2019, one in ten of our Mac security solutions encountered this malware at least once, and it accounts for almost 30% of all detections for this OS. The first specimens of this family fell into ...
- European Energy Sector Organization Targeted by PupyRAT Malware in Late 2019
January 23, 2020
Over the course of the last year, Recorded Future research has demonstrated that Iran-nexus groups, possibly including APT33 (also called Elfin), have been prolific in amassing operational network infrastructure throughout 2019. Additionally, in November 2019, Microsoft disclosed that APT33 had shifted focus from targeting IT networks to physical control systems used in electric utilities, manufacturing, and oil refineries. We ...
- Jeff Bezos hack: Amazon boss’s phone ‘hacked by Saudi crown prince’
January 22, 2020
The Amazon billionaire Jeff Bezos had his mobile phone “hacked” in 2018 after receiving a WhatsApp message that had apparently been sent from the personal account of the crown prince of Saudi Arabia, sources have told the Guardian. The encrypted message from the number used by Mohammed bin Salman is believed to have included a malicious file that infiltrated ...
