EUVD-2006-0405

Malware in sbrugna...

EUVD-2021-21880

Malware in sbrugna...

EUVD-2025-18993

Malicious code in bioql PyPI...

PT-2025-38593

Name of the Vulnerable Software and Affected Versions Vasion Print formerly PrinterLogic Virtual Appliance Host and Application Description The Windows client components PrinterInstallerClientInterface.exe, PrinterInstallerClient.exe, PrinterInstallerClientLauncher.exe lack modern exploit...

Giving AI Agents Access to Cryptocurrency and Smart Contracts Creates New Vectors of AI Harm

There is growing interest in giving AI agents access to cryptocurrencies as well as to the smart contracts that transact them. But doing so, this position paper argues, could lead to formidable new vectors of AI harm. To support this argument, we first examine the unique properties of...

CVE-2025-48466

Successful exploitation of the vulnerability could allow an unauthenticated, remote attacker to send Modbus TCP packets to manipulate Digital Outputs, potentially allowing remote control of relay channel which may lead to operational or safety risks...

CVE-2025-48466 Modbus Command Injection without Authentication

Successful exploitation of the vulnerability could allow an unauthenticated, remote attacker to send Modbus TCP packets to manipulate Digital Outputs, potentially allowing remote control of relay channel which may lead to operational or safety risks...

CVE-2025-48466

CVE-2025-48466 is linked to Advantech WISE-4060LAN and related models (WISE-4010LAN, WISE-4050LAN). The issue allows an unauthenticated, remote attacker to send Modbus TCP packets to manipulate Digital Outputs, potentially enabling remote control of relay channels and creating operational/safety ...

PT-2025-26678

Name of the Vulnerable Software and Affected Versions: The product name cannot be determined. Description: The issue allows an unauthenticated, remote attacker to send Modbus TCP packets to manipulate Digital Outputs. This could potentially allow remote control of the relay channel, leading to...

Towards Understanding the Cognitive Habits of Large Reasoning Models

Large Reasoning Models LRMs, which autonomously produce a reasoning Chain of Thought CoT before producing final responses, offer a promising approach to interpreting and monitoring model behaviors. Inspired by the observation that certain CoT patterns -- e.g., "Wait, did I miss anything?'' --...

CVE-2025-46352

The CS5000 Fire Panel is vulnerable due to a hard-coded password that runs on a VNC server and is visible as a string in the binary responsible for running VNC. This password cannot be altered, allowing anyone with knowledge of it to gain remote access to the panel. Such access could enable an...

CVE-2025-46352 Consilium Safety CS5000 Fire Panel Use of Hard-coded Credentials

The CS5000 Fire Panel is vulnerable due to a hard-coded password that runs on a VNC server and is visible as a string in the binary responsible for running VNC. This password cannot be altered, allowing anyone with knowledge of it to gain remote access to the panel. Such access could enable an...

Analysing Safety Risks in LLMs Fine-Tuned with Pseudo-Malicious Cyber Security Data

The integration of large language models LLMs into cyber security applications presents significant opportunities, such as enhancing threat analysis and malware detection, but can also introduce critical risks and safety concerns, including personal data leakage and automated generation of new...

Exploit for Cross-site Scripting in Phpgurukul Hospital_Management_System

CVE-2023-7173: Stored Cross-Site Scripting XSS in Hospital M...

Meta’s Purple Llama wants to test safety risks in AI models

Meta has announced Purple Llama, a project that aims to "bring together tools and evaluations to help the community build responsibly with open generative AI models." Generative Artificial Intelligence AI models have been around for years and their main function, compared to older AI models is th...

81% concerned about ChatGPT security and safety risks, Malwarebytes survey shows

Seven months after ChatGPT burst into our lives, it seems the lustre of the chatbot-that's-going-to-change-everything is starting to fade. A new survey by Malwarebytes exposes deep reservations about ChatGPT, with optimism in startlingly short supply. Of the respondents familiar with ChatGPT: 81%...

Vulnerability disclosure buzzword bingo!

Play Buzzword Bingo With Us! In the last 5 or so years of research we’ve found a substantial number of products with vulnerabilities in their supporting apps and infrastructure, as well as in the devices themselves. Some were low-impact, some were just curiosities, but many critical flaws exposin...

FDA Issues Security Guidelines For Medical Device Manufacturers

Hoping to strengthen the security of medical devices, the Food and Drug Administration today issued a new series of guidelines for manufacturers. The document was released to encourage companies to mitigate viruses and malware on devices such as defibrillators, insulin pumps and pacemakers before...