LIVE · cybersecurity feed
Live wire
CVE-2024-3848 · LFProjects MLflow Path Traversal Vulnerability Added To VulnCheck KEVCVE-2026-118267 · WPDataAccess Incorrect Authorization Flaw Exploited Same Day As DisclosureCVE-2026-118066 · LatePoint Improper Authentication Vulnerability Exploited On Day Of DisclosureCVE-2026-132224 · Optimizely Web Experimentation Flaw Exploited Same Day as DisclosureCVE-2026-133968 · Project-MONIA MONAI Label Path Traversal Exploited On Disclosure DateCairn AI Framework Used in Autonomous Zero-Day ExploitationAmazon: China-Linked Hackers’ AI Agents Exploited Medical Software Zero-DayCVE-2026-129975 · GnuPG Warns Critical GPGME Flaw Could Expose App Data via Malicious OpenPGP KeysCVE-2026-129448 · Hackers Exploit Critical VMware, Cisco, and Apache Flaws as Espionage Attacks EmergeCTO of ‘RansomwareHelp’ Indicted for Wire Fraud
vulnerability

Attackers' AI Agents Found a Zero-Day in Medical-Imaging Software and Gained Root Access

Security researchers have identified a significant security breach involving the exploitation of a zero-day vulnerability within MONAI Label, an open-source framework used for medical imaging. According to threat intelligence reports, suspected China-linked actors utilized autonomous AI agents to discover and weaponize this previously unknown flaw. The exploit reportedly allowed unauthorized…

ZeroDay News ·

Source: The Hacker News

Security researchers have identified a significant security breach involving the exploitation of a zero-day vulnerability within MONAI Label, an open-source framework used for medical imaging. According to threat intelligence reports, suspected China-linked actors utilized autonomous AI agents to discover and weaponize this previously unknown flaw. The exploit reportedly allowed unauthorized parties to gain root-level access to a university server hosting the software.

The vulnerability resides in the way the server handles file operations, specifically allowing an attacker without valid credentials to write files outside of the designated storage directory. This type of flaw, often categorized as a directory traversal or arbitrary file write vulnerability, can be particularly dangerous when it allows an attacker to place malicious scripts or configuration files in sensitive system locations. By manipulating the server's file system interactions, the attackers were able to escalate their privileges to the root level, effectively taking full control of the host machine.

The issue affects MONAI Label version 0.8.5 and all prior iterations when deployed in their default configuration. Because the software is designed to facilitate the annotation and training of medical imaging models, it often runs with elevated permissions to interact with large datasets and system resources. When such applications are exposed to the internet, they become high-value targets for automated discovery tools, including the AI-driven agents reportedly used in this incident.

In this class of vulnerability, mitigation typically involves restricting the application's file system permissions to the absolute minimum required for operation and ensuring that the software is not exposed to public-facing networks without robust authentication layers. Developers and system administrators are generally advised to implement strict input validation and path sanitization to prevent unauthorized file operations. Organizations using affected versions are encouraged to audit their server logs for signs of unauthorized file writes or unusual privilege escalation attempts.

The use of autonomous AI agents to identify and exploit zero-day vulnerabilities represents an evolving challenge for cybersecurity defense. While automated vulnerability scanning has long been a component of both offensive and defensive operations, the integration of AI agents suggests a shift toward more efficient, rapid discovery of flaws in complex software stacks. This incident highlights the increasing necessity for rigorous security auditing in open-source projects that handle sensitive data, particularly as the barrier to entry for exploiting sophisticated software continues to lower.

vulnerabilityzero-dayai
ShareXLinkedInWhatsAppFacebook

More News

view all →
CVE-2024-3848high

LFProjects MLflow Path Traversal Vulnerability Added To VulnCheck KEV

The LFProjects MLflow path traversal vulnerability, CVE-2024-3848, has been added to the VulnCheck KEV catalogue, 894 days after its initial publication.

CVE-2026-118267high

WPDataAccess Incorrect Authorization Flaw Exploited Same Day As Disclosure

The wp_data_access plugin for WordPress faces active exploitation following a zero-day disclosure, yet it remains absent from major federal vulnerability catalogues.

CVE-2026-118066high

LatePoint Improper Authentication Vulnerability Exploited On Day Of Disclosure

The LatePoint plugin for WordPress is currently under exploitation, with the vulnerability appearing in the VulnCheck KEV catalogue on the same day it was published.

CVE-2026-132224high

Optimizely Web Experimentation Flaw Exploited Same Day as Disclosure

CVE-2026-132224 was identified as exploited on the same day it was published, leaving organizations with no time to patch before active exploitation began.

patch

Weekly Update 531: Optimizely. Script Dependencies & Third Parties

A recent disclosure notice regarding Optimizely has highlighted ongoing concerns surrounding the security of third-party script dependencies. The incident underscores a growing trend where organizations point to external vendors when explaining security lapses, a practice that critics argue serves to deflect institutional accountability rather than addressing the underlying technical risks.

nation-state

FBI Investigating Apparent Hack of Its Key National Criminal Justice Database, AP Source Says

The Federal Bureau of Investigation is currently conducting an investigation into a potential security breach involving the National Crime Information Center, a critical repository of criminal justice data. The database, which is managed by the FBI, serves as a centralized resource for federal, state, and local law enforcement agencies. It contains sensitive information including records on…