agentic AI
Wirken: Open-source AI agent gateway
Wirken is an open-source gateway that sits between messaging apps and AI agents. It assumes any agent can be turned against its owner and limits what a compromised one can …
OpenAI’s GPT-6 Cyber found 81 Firefox flaws earlier AI testing missed
OpenAI has introduced GPT-6 Cyber, a version of GPT-6 Astra trained to find software vulnerabilities, test how attackers could exploit them, and help develop fixes. The model …
87% say their AI controls need to work better
The AI running inside large companies has stopped waiting for permission. Across five categories of AI, from chatbots to process automation, more than half of 3,600 business …
99% of repository access tokens never expire
Developers, automated tools and AI coding agents hold permissions that can outlast the work they were granted for. Without access reviews, organizations can leave accounts …
Google puts new limits on AI agents that hunt threats and fix vulnerabilities
Google Cloud is adding new controls to CodeMender, its AI tool for finding and fixing software vulnerabilities, allowing businesses to isolate attack simulations and target …
AI agent detection signals that still work when agents look human
Bots follow a script. AI agents work toward a goal and choose their own steps, which makes them harder to catch. In this Help Net Security interview, Zohaib Ahmed, CEO of …
Most consumers aren’t ready to let AI agents shop unsupervised
Customer control, account security and ease of use are influencing the adoption of AI agents that make purchases, book services and access personal information, according to …
AI agents scale and speed up Chinese-linked attacks
A China-nexus espionage group used AI agents to attack more than 200 organizations in 11 days, CrowdStrike said last week. On Monday, Kaspersky published details of a separate …
Ransomware gang talked AI agents into doing much of its dirty work
The group behind the Aur0ra ransomware has been using AI agents to move through victim networks, collect credentials and work its way up to domain administrator access, …
Open-weight AI model GLM-5.3 cheated its way to correct answers
Irregular evaluated Zhipu AI’s open-weight model GLM-5.3 across 13 offensive cyber scenarios using CyScenarioBench, the company’s framework for measuring an LLM’s ability to …
Google says Gemini 4 Carbon beats its predecessors at finding and fixing security flaws
Google’s Gemini 4 Carbon is a frontier AI model designed for software engineering and cybersecurity tasks, with safeguards built on those of its predecessor, Argon. SEC-bench …
Upwind secures $400 million to protect AI across endpoints, code, and cloud
Upwind Security has raised $400 million in Series C funding to expand its cloud and AI security platform, bringing the company’s total funding to more than $800 million. …
Featured news
Resources
Don't miss
- Fake GTA 6 download goes after Steam logins and crypto wallet data
- Stolen webcam clips of 900+ victims feed North Korea’s $400 million fake Zoom scheme
- How attackers turned a Teams meeting booking into a device code phishing trap
- Suspected North Korean IT workers reached onboarding at companies with open data
- Your pinned MCP server may not be as pinned as you think