433 Central Ave., 4th Floor, St. Petersburg, FL 33701 | info@poseidon-us.com | Office: (813) 563-2652

When trusted AI connections turn hostile

Researchers have revealed a new security blind spot in how LLM applications connect to external systems. Their study shows that malicious Model Context Protocol (MCP) servers can quietly take control of hosts, manipulate LLM behavior, and deceive users, all while staying undetected by existing tools. MCP servers, which act as connectors that let AI systems access files, tools, and online data, can be turned into active threats. They are easy to create, hard to detect, … More → The post When trusted AI connections turn hostile appeared first on Help Net Security.
http://news.poseidon-us.com/TNjDHq

Identifying risky candidates: Practical steps for security leaders

Effective insider threat defense begins with candidate vetting. Background checks and reference calls can confirm elements of an applicant’s history, but they rarely surface the deeper risks that can turn into costly problems down the line. Identity verification, credential validation, and digital risk assessments need to be layered into the hiring process. Indicators such as reused or doctored photos, a minimal online presence, or newly created social media accounts can signal that a candidate may … More → The post Identifying risky candidates: Practical steps for security leaders appeared first on Help Net Security.
http://news.poseidon-us.com/TNj8c4

Everyone wants AI, but few are ready to defend it

The rush to deploy AI is reshaping how companies think about risk, according to Cisco. A global study finds that while most organizations are moving quickly to adopt AI, many are not ready for the pressure it puts on their systems and security. A small group of companies have managed to stay ahead. These “Pacesetters” treat AI readiness as part of their long-term strategy. They plan for scale, build solid infrastructure, and take security seriously. … More → The post Everyone wants AI, but few are ready to defend it appeared first on Help Net Security.
http://news.poseidon-us.com/TNj8ZN

Humanoid robot found vulnerable to Bluetooth hack, data leaks to China

Alias Robotics has published an analysis of the Unitree G1 humanoid robot, concluding that the device can be exploited as a tool for espionage and cyber attacks. A robot that can be hacked through Bluetooth Their tests show that anyone within Bluetooth range can exploit the setup process to inject commands and gain root access, taking control of the robot. The problem lies in how it handles its setup process over Bluetooth Low Energy (BLE). … More → The post Humanoid robot found vulnerable to Bluetooth hack, data leaks to China appeared first on Help Net Security.
http://news.poseidon-us.com/TNj6QP

The password problem we keep pretending to fix

Experts across industries say they are still losing ground against identity-related breaches, even after years of investment in stronger access controls, according to RSA. Many said their organizations had faced at least one identity-related breach in recent years, and most of those incidents caused operational damage. These breaches often start with everyday gaps such as password reuse, weak verification, and overconfidence in aging systems. Once attackers gain access through a compromised account, they can move … More → The post The password problem we keep pretending to fix appeared first on Help Net Security.
http://news.poseidon-us.com/TNj6Pm

ImmuniWeb Expands discovery with ASM and Dark web packages

On top of several new free tools launched during the summer, ImmuniWeb released over 500 updates, improvements, new features, and integrations across all our products in Q3, including ImmuniWeb On-Demand, ImmuniWeb MobileSuite, ImmuniWeb Continuous, ImmuniWeb Neuron, ImmuniWeb Neuron Mobile, and ImmuniWeb Discovery. ImmuniWeb has added two new packages to ImmuniWeb Discovery, its flagship Continuous Threat Exposure Management (CTEM) solution: ASM (attack surface management) package: designed for organizations of any size that need to have a … More → The post ImmuniWeb Expands discovery with ASM and Dark web packages appeared first on Help Net Security.
http://news.poseidon-us.com/TNj46F