The Hacker News | #1 Trusted Source for Cybersecurity News — Index Page

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 your computer. Neither trick hijacks the agent's task. Each one just corrupts the facts it trusts and lets it carry on with the job you asked for. That is the shape of a new class of attack laid out in a  paper posted July 6  by researchers from Seoul National University, the University of Illinois Urbana-Champaign, and Largosoft. They call it agent data injection , or ADI. The attacker's input gets dressed up as data the agent already trusts, like a sender's name or a button's ID, so it slips past most of the defenses built to stop prompt injection. The gap comes from how an agent reads. It takes in two kinds of things: instructions, meaning what you and the app's developer tell it to d...

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 evidence indicating its use in targeted attacks aimed at governments and other critical infrastructure targets since 2013. The latest findings from the Symantec and Carbon Black Threat Hunter Team show that Daxin is still operational, after it was found running on a compromised host in Taiwan in 2026. The same machine, belonging to a Taiwan-based subsidiary of a multinational high-tech manufacturer, is also said to have been infected with Stupig ("a.dll" or "kbdus1.dll"). The file name is an attempt to masquerade as "kbdus.dll," a legitimate Microsoft DLL associated with the U.S. English keyboard layout...

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. That is a real advantage for security teams. It also creates a new kind of pressure, because the industry can now produce more vulnerability-looking output than ever before. The problem is that output is not the same as evidence. A generated report can sound polished, include a severity rating, and even contain a proof-of-concept that looks reasonable at first glance. None of that proves the bug exists in the deployed environment. None of it proves exploitability, impact, or risk. In offensive testing, the hard part has never been writing something that sounds like a vulnerability report. The hard part is demonstrating what is actually true. That d...

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 publishing under the handle tokay0  put the method online  on Monday, having tested it only against vacuums he bought himself. The flaw was unpatched then. He says SharkNinja, the company behind the Shark and Ninja appliance brands, has had his report since March. The policy attached to that certificate was never scoped to the device holding it. Present it to Shark's cloud broker, and the broker accepts whatever you publish, addressed to any device it serves. No memory corruption, no privilege escalation, no password to guess. The command that runs is an ordinary field in the device shadow, the per-device state document AWS keeps in the cloud. Using the certificate from an RV2320EDUS, the rese...

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) company said . "We use GPT‑Red to adversarially train GPT‑5.6 , making it much more robust to prompt injections." The model works just like a human red-teamer. It sends a prompt, monitors how a GPT model responds, and iterates its way towards a malicious goal, such as uploading sensitive data to an external server. The development comes as adversarial prompt injections continue to be a persistent thorn in the flesh of large language models, which can be tricked into executing a carefully crafted instruction⁠ that can produce undesirable consequences. As agentic systems continue to be hooked to third-party data sources ...

Zoom has released security updates for a critical security flaw impacting Zoom Workplace for Windows that could facilitate account takeover. The vulnerability, tracked as CVE-2026-53412 (CVSS score: 9.8), affects Zoom Workplace for Windows before version 7.0.0 and Zoom Workplace VDI Client for Windows before version 7.0.10, 6.6.15, and 6.5.18 in their respective branches. "Improper Input Validation in Zoom Desktop Client for Windows and Zoom VDI Client for Windows may allow an unauthenticated user to conduct an account takeover via network access," Zoom said in an advisory released this week. The latest security fixes also address three high-severity flaws - CVE-2026-53411 (CVSS score: 7.8) - An improper input validation vulnerability in the Zoom Workplace VDI Plugin for Windows before version 6.6.14 that may allow an authenticated user to conduct an escalation of privilege via local access. CVE-2026-53410 (CVSS score: 7.0) - A time-of-check to time-of-use ...

Cybersecurity researchers have disclosed details of a previously unreported Internet-of-Things (IoT) botnet framework dubbed TuxBot v3 Evolution that shows signs of being developed with assistance from a large language model (LLM), albeit with not so successful results. "While the AI complied with their request to generate botnet code, it included a safety disclaimer that the developer failed to remove before shipping," Palo Alto Networks Unit 42 said . "Although the LLM clearly aided in constructing the botnet, several functions in the analyzed samples failed to work correctly." The cybersecurity company said a manual code review would have resolved these errors and that it's possible more polished iterations of the malware exist out there in the wild. The botnet framework consists of multiple components: a C-based bot agent that cross-compiles for multiple architectures (e.g., ARM, MIPS, MIPSEL, MIPS64, x86_64, PowerPC, and RISC-V), a Go-based command-...