Ask an AI agent to summarize the reviews on a product page, and a single planted review can make it click “Buy Now” instead. Ask a coding assistant to apply a maintainer’s fix from a GitHub thread, and a fake comment can make it run a stranger’s command on yourRead More »New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker Commands
The startup has built an AI-powered Identity Operating System that governs all identities across an organization’s environment. The post Oak Emerges From Stealth Mode With $60 Million in Funding appeared first on SecurityWeek.
An advanced malware previously attributed to a China-linked threat actor has resurfaced after more than four years within a Taiwan manufacturing firm, along with a previously unreported backdoor dubbed Stupig. Daxin (“srt64.sys”), as the kernel-mode rootkit is referred to, was first documented by Broadcom-owned Symantec in March 2022, with evidenceRead More »Daxin Resurfaces in Taiwan Alongside Stupig Pre-Login SYSTEM Backdoor
The flaws could allow attackers to access credentials and data, take over accounts, and escalate their privileges. The post Splunk, Zoom Patch Critical Vulnerabilities appeared first on SecurityWeek.
Artificial intelligence (AI) is changing offensive security, but it has not changed the standard that matters most: a finding has to be proven before it becomes useful. AI-assisted tools can read code quickly, generate payloads, summarize attack surfaces, explain unfamiliar APIs, and run repetitive testing workflows at impressive speed. ThatRead More »AI Can Find Bugs, But Human Knowledge Still Proves Them
Pull the certificate off the flash of a Shark RV2320EDUS robot vacuum, and you can run root commands on other people’s Shark vacuums across the same AWS region: watch the camera, drive the robot, read the map of the house, and take the Wi-Fi password in plaintext. A researcher publishingRead More »Unpatched Shark Vacuum Flaw Could Let Attackers Control Other Vacuums Region-Wide
Attackers could exploit the bugs to modify configurations, terminate or restart processes, cross security boundaries, leak memory, and execute code. The post F5 Patches Multiple NGINX, BIG-IP Vulnerabilities appeared first on SecurityWeek.
Chinese cybersecurity firms are facing action from the country’s military, but it’s not due to product or technical failures. The post China’s Top Cybersecurity Firms Hit by Mounting Military Procurement Bans appeared first on SecurityWeek.
OpenAI has disclosed details of GPT-Red, an internal automated red-teaming model that scales prompt injection vulnerability discovery with an aim to fix issues before the tools are deployed widely. “GPT‑Red is a strong red-teamer, and our previous models are highly vulnerable to its prompt injection attacks,” the artificial intelligence (AI)Read More »OpenAI’s GPT-Red Automates Prompt Injection Testing to Harden GPT-5.6 Sol
Signed by Microsoft, the vulnerable UEFI shim bootloaders could be abused on any system, regardless of the OS. The post Old UEFI Shims Expose Systems to Secure Boot Bypass appeared first on SecurityWeek.
