Researchers Demonstrate Ghostscript Sandbox-Escape RCE via Crafted File Uploads in Popular Apps

A now-patched flaw in Ghostscript allows a crafted file to escape the program’s security sandbox and run commands on the server that processes it. Ghostscript is the interpreter that many Linux servers use to convert uploaded PDFs, PostScript files, and images into other formats, often without the application calling it directly. Security firm pwn.ai showed … Weiterlesen

OpenRouter Drops 3 Providers After Researchers Catch Months of Prompt Theft at AI Hosting Firms

Attackers stole data from inside three AI inference providers for months, and none of the three knew until researchers told them, the industrial cybersecurity company Dragos said this week. Some of the stolen requests were flagged as Zero Data Retention, the setting that is supposed to mean a prompt is never stored. OpenRouter, a gateway … Weiterlesen

A Single Malicious Webpage Let Researchers Hijack Meta Muse and Access Private Chats

A malicious webpage could extract a Meta Muse user’s private conversations and stored memories from the assistant without triggering any approval prompt, researchers have shown. The same attack could be extended to reach the credentials Muse stores for the user’s connected accounts. The work was a laboratory demonstration, not an attack on real users, and … Weiterlesen

Hackers Exploit Critical VMware, Cisco, and Apache Flaws as Espionage Attacks Emerge

The U.S. Cybersecurity and Infrastructure Security Agency (CISA) on Friday added four flaws impacting Apache Roller, Cisco Expressway, SAP NetWeaver, and Broadcom VMware vCenter to its Known Exploited Vulnerabilities (KEV), citing evidence of active exploitation. The vulnerabilities are listed below – CVE-2026-129448 (CVSS score: 9.8) – A deserialization of untrusted data vulnerability in Quelle: Zum … Weiterlesen

Signal Blocks AI Agents From Reading Private Chats via Screenshots on Android and iOS

Signal has announced that it will restrict screenshots by default to stop artificial intelligence (AI) agents from reading private chats on Android and iOS devices, but conceded that the protection is „incomplete.“ The feature applies to agentic systems built into iOS 27 and on Android versions where the encrypted messaging platform can detect an AI … Weiterlesen

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

Suspected China-linked hackers used autonomous AI agents to find a previously unknown flaw in MONAI Label, an open-source medical imaging server, and gain root access to a university server, Amazon Threat Intelligence said this week. The flaw allows an attacker with no account to write files outside the server’s storage folder, and it affects MONAI … Weiterlesen

GnuPG Warns Critical GPGME Flaw Could Expose App Data via Malicious OpenPGP Keys

A malicious OpenPGP key with an unusually long user ID can trigger a critical memory bug in GPGME, the standard library that programs use to work with GnuPG. The GnuPG project warned yesterday that the flaw could be used to steal data from affected applications and has released fixed versions. The bug, tracked as CVE-2026-129975, … Weiterlesen

WhatsApp Patches 3 Security Flaws, Including Android Bug Suspected of Use in Scams

Meta-owned WhatsApp has addressed security vulnerabilities, including one impacting its Android app that it suspects may have been exploited in connection with scam messages. The vulnerability, tracked as CVE-2026-23871, has been described as a case of incomplete validation of external ad-reply URLs in WhatsApp for Android and WhatsApp Business for Android before 2.26.17.4. The issue … Weiterlesen

The Path to AI Autonomy in the SOC

Security leaders are about to hand AI agents a lot more authority. In a recent a16z survey of CISOs at organizations with more than 1,000 employees, 36% said they are comfortable today letting AI agents act autonomously on low-risk security actions. In 12 months from now, 60% expect to be comfortable at that level. Overall, … Weiterlesen

Linux KVM Flaw CVE-2026-99312 Lets Guest VMs Access Host Memory on AMD Hosts

A flaw in KVM, the hypervisor built into the Linux kernel, let researchers read about 127 GB of a cloud server’s memory from inside a virtual machine of their own on DigitalOcean. On a shared server, that memory can include other customers‘ virtual machines. The flaw, tracked as CVE-2026-99312, affects only hosts with AMD processors … Weiterlesen