‘ZombieAgent’ zero click vulnerability allows for silent account takeover


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:

  • Indicators of Compromise Associated with Cuba Ransomware

    December 2, 2021

    The FBI has identified, as of early November 2021 that Cuba ransomware actors have compromised at least 49 entities in five critical infrastructure sectors, including but not limited to the financial, government, healthcare, manufacturing, and information technology sectors. Cuba ransomware is distributed through Hancitor malware, a loader known for dropping or executing stealers, such as ...

  • Colorado energy company loses 25 years of data after cyberattack while still rebuilding network

    December 2, 2021

    Colorado’s Delta-Montrose Electric Association (DMEA) is still struggling to recover from a devastating cyberattack last month that took down 90% of its internal systems and caused 25 years of historical data to be lost. In an update sent to customers this week, the company said it expects to be able to begin accepting payments through its ...

  • Hackers are turning to RTF template injections technique to install malware on PCs

    December 2, 2021

    Nation state-backed hacking groups are exploiting a simple but effective new technique to power phishing campaigns for spreading malware and stealing information that’s of interest to their governments. Cybersecurity researchers at Proofpoint say advanced persistent threat (APT) groups working on behalf of Russian, Chinese and Indian interests are using rich text format (RTF) template injections. While the ...

  • APT Expands Attack on ManageEngine With Active Campaign Against ServiceDesk Plus

    December 2, 2021

    Over the course of three months, a persistent and determined APT actor has launched multiple campaigns which have now resulted in compromises to at least 4 additional organizations, for a total of 13. Beginning on Sept. 16, 2021, the U.S. Cybersecurity and Infrastructure Security Agency (CISA) released an alert warning that advanced persistent threat (APT) ...

  • Vulnerability Spotlight: Use-after-free condition in Google Chrome could lead to code execution

    December 2, 2021

    Cisco Talos recently discovered an exploitable use-after-free vulnerability in Google Chrome. Google Chrome is a cross-platform web browser — and Chromium is the open-source version of the browser that other software developers use to build their browsers, as well. This specific vulnerability exists in Blink, the main DOM parsing and rendering engine at the core of ...

  • Play Your Cards Right: Detecting Wildcard DNS Abuse

    December 1, 2021

    The domain name system (DNS) maps names to addresses so that computers can communicate. The directions within the DNS exist largely in records where a specific name (such as paloaltonetworks.com) is mapped to pieces of data, such as IP addresses (for example, 34.107.151202). As the name suggests, wildcard DNS records are an exception to this ...