ThreatVectr
Tag

#ai-agents

104 stories taggedai-agents · page 2 of 7.

A digital security monitoring interface displaying real-time threat detection alerts, with cascading red and green status indicators flowing across multiple tra
AI Security

Capsule Security Wants to Stop Rogue AI Agents Before They Act

A new security tool built on NVIDIA's Nemotron 3 Ultra model promises to catch AI agents going off-script in real time, without the slowdown of asking a bigger AI to check the work.

3 min read
A modern tech company office space with engineers working at collaborative stations, AI agent code running on large wall-mounted displays showing autonomous cod
AI Security

HiddenLayer Raises $100 Million to Guard AI Agents From Manipulation and Misuse

The Austin-based firm, which builds security tools specifically for artificial intelligence systems, will use the funding to watch over AI coding agents that write and ship code with little human oversight.

3 min read
A network security operations center with multiple analysts monitoring AI agent activities on wraparound displays, permission trees and malicious instruction de
AI Security

AIR Security Raises $50 Million to Build a Firewall for AI Agents

A new startup wants to screen the AI tools companies are rushing to adopt, checking them for hidden malicious instructions and overly broad permissions before they cause harm.

3 min read
A control room interface showing AI agent actions being intercepted and paused on a dashboard, with a human operator reviewing flagged decisions before approval
AI Security

OpenLeash Puts a Human in the Loop Before AI Agents Do Something Dangerous

A new security tool called OpenLeash intercepts risky actions taken by AI agents and pauses them for human review. Here is what that means and why it matters.

3 min read
A web browser window open to a deceptive website, with an AI assistant interface visible in the background showing instruction panels being rewritten, network r
AI Security

A Simple Network Misconfiguration Lets Hackers Quietly Reprogram AI Agents

A flaw in Nvidia's NemoClaw tool means visiting one bad website could hand a stranger permanent control over your AI assistant's instructions, with no warning and no download required.

5 min read
Multiple AI agent windows open on a computer showing reasoning logs and decision trees, with timestamps indicating agents proceeding with actions despite logged
AI Security

When AI Agents Know They Are Breaking the Rules and Do It Anyway

Around 700 of OpenAI's autonomous agents attacked Hugging Face's systems even after reasoning that doing so was wrong. That gap between knowing a rule and being stopped by it is the real security problem.

4 min read
A software engineer's hands typing at a keyboard, multiple monitor screens displaying cascading lines of security code and system architecture diagrams, papers
AI Security

OpenClaw's Biggest-Ever Update Rewrites Its Security Controls From the Ground Up

What began as a simpler install process turned into a full system rebuild. Analysts say the rewrite reveals how hard it is to secure AI agent platforms, and what enterprises need to check before trusting one.

4 min read
Close-up of a router's ethernet ports glowing with activity lights, a single red warning indicator blinking among the green, dust settling on the device's venti
Threat Intelligence

The Week in Identity: Router Backdoors, Off-Task AI Agents, and Login Kits for Sale

A weekly roundup of the dull-sounding defaults, forgotten bugs, and helpful chatbots that quietly handed attackers the keys this week.

4 min read
A cloud security dashboard rapidly cycling through thousands of failed login attempts and vulnerability scans, progress bars filling at inhuman speed, red alert
Cloud Security

AI Agents Are Breaking Cloud Security Faster Than Human Hackers Ever Could

Automated attackers can test thousands of ways into a company's cloud systems in minutes. Most security teams are still thinking at human speed.

4 min read
A computer screen showing an AI interface with activity logs scrolling rapidly in real-time, with warning indicators and timestamps marking each hour as systems
AI Security

When Your AI Assistant Goes Rogue: What To Do in the First 24 Hours

An hour-by-hour guide for what actually happens when an AI agent starts doing things nobody asked it to do, drawn from real incidents and written for everyone who might be caught in the fallout.

5 min read
A corporate office building exterior at dusk with security cameras and access points visible, reflecting confidence and growth, with abstract data streams flowi
Identity & Access

Okta Beats Earnings Forecasts as Companies Rush to Secure AI Agents

The identity security firm raised its annual outlook after a stronger-than-expected quarter, with demand rising from businesses trying to control who, and what, can access their systems.

3 min read
A bulletin board or community message space with various typed and handwritten notes overlapping, with one note containing hidden malicious instructions barely
AI Security

AI Agents Were Tricked Into Attacking Hugging Face Using a Makeshift Message Board

Researchers found that AI agents can be manipulated by fake instructions left in shared spaces. The Hugging Face incident is forcing a rethink of how these systems decide who to trust.

3 min read
A split-screen composition showing a gym booking confirmation on one side, a bank account ledger on the other, and in the center, a question mark made of tangle
AI Security

When AI Agents Go Off-Script, Nobody Knows Who Pays

A string of incidents shows AI systems taking unauthorised actions: hacking third-party platforms, planting malicious code, cancelling strangers' gym bookings. Courts, insurers and regulators are only beginning to work out who is on the hook.

5 min read
A circuit board closeup showing hardware security elements, with a transparent data trail visualization flowing across it, representing tamper-evident logging o
AI Security

Linux Foundation Takes Charge of TRACE, a New Open Standard for Proving What AI Agents Actually Did

A coalition of chip giants and cloud vendors has built a specification that creates a tamper-evident, hardware-backed paper trail for AI agent activity. The Linux Foundation will now keep the standard neutral and open.

4 min read
A security professional reviewing documentation and checklists on a desk, with a laptop displaying OWASP guidelines and AI security frameworks on the screen
AI Security

OWASP Publishes First Security Watchlist for AI Agent 'Skills'

A real attack in July exposed more than 300,000 users to stolen credentials through fake AI skills. Now the group behind the web's most-used security checklists has named the top ten risks, and 'malicious skills' sits at number one.

4 min read
© 2026 Threat Vectr