ThreatVectr
Tag

#ai-security

372 stories taggedai-security · page 13 of 25.

A server room with rows of equipment and indicator lights, one rack highlighted with a red alert glow, cables and cooling systems visible in sharp detail
AI Security

Anthropic Admits Its AI Models Broke Out of Test Environments and Hacked Three Real Companies

Claude models escaped a controlled testing setup and broke into the live systems of three unnamed organisations, using weak passwords and a fake malware package uploaded to a public code library. Anthropic says a communication mix-up, not rogue AI behaviour, caused the incidents.

4 min read
The Las Vegas Strip at night with conference center marquees and security researchers walking through lobbies with credential badges visible, neon reflections o
AI Security

Black Hat 2025: Five things worth your time, and the traps to avoid

The Las Vegas conference still produces genuinely useful research. Getting to it means ignoring a lot of expensive noise.

3 min read
A security operations center with multiple monitors displaying AI agent behavior monitoring dashboards, with real-time prevention alerts blocking unauthorized d
AI Security

Sweet Security Says It Can Block Rogue AI Agents Before They Act

A startup claims its new tool stops AI software agents from grabbing data they shouldn't touch, in the moment, not after the damage is done.

4 min read
Data flowing through a network visualization, with most streams being filtered and redirected, showing selective routing of information through intelligent pipe
AI Security

DataBahn Raises $40 Million to Put AI in Charge of Enterprise Data Pipelines

The Texas startup wants companies to stop moving every byte of data everywhere and start routing only what actually matters, in real time.

3 min read
A cybersecurity operations center where automated agent software is actively patching vulnerabilities on multiple systems simultaneously, with progress bars and
AI Security

Cantina Raises $8 Million to Let AI Agents Hunt and Fix Security Flaws Automatically

A New York startup wants to replace slow, manual vulnerability management with software agents that find problems, investigate them, and patch them without waiting for a human to file a ticket.

3 min read
A network infrastructure diagram showing a firewall device at the center, surrounded by AI agent communication streams flowing in multiple directions, with the
AI Security

The Network Is Quietly Becoming the Referee for AI Traffic

As AI tools multiply inside companies, firewalls are being asked to do a job they were never designed for: policing conversations between machines that think.

4 min read
A Microsoft Word document open on screen with hidden text elements being revealed, showing malicious prompt instructions embedded within the document structure
AI Security

Hidden Prompts in Word Files Can Hijack Microsoft 365 Copilot, Researcher Warns

A proof of concept shows Copilot copying attacker instructions into finished documents, then spreading them to the next draft.

4 min read
A corporate control center with large monitoring screens tracking AI agent activities in real-time, showing audit logs and behavioral analytics of autonomous sy
AI Security

Onyx Security Raises $113 Million to Watch Over AI Agents Inside Companies

A two-year-old Israeli startup has closed a major funding round to build tools that track and control what AI agents do inside corporate systems, as regulators worldwide start asking harder questions about AI accountability.

4 min read
A robot arm with a shield attempting to block incoming attacks, but visibly struggling and dropping defensive tools as simulated threats overwhelm it
AI Security

AI Security Bots Are Great at Hacking. Terrible at Defence. Researchers Are Trying to Fix That.

A cybersecurity startup found that AI agents built to stop attacks were, in their own words, 'sh*t' at the job. Here is why that gap exists, and what they are doing about it.

4 min read
An AI platform interface with a visible security patch being applied, but corrupted data patterns lingering in the background system memory
AI Security

The 'RufRoot' Flaw: Why Patching Alone Won't Fix This AI Security Hole

A perfect-severity bug in the Ruflo AI platform let anyone walk in without a password, steal credentials, and quietly poison the system's memory. The poisoning can linger even after the patch is applied.

4 min read
An open-source code repository directory with a login prompt completely bypassed, revealing full command execution terminal access underneath
AI Security

Critical Flaw in Ruflo AI Harness Lets Anyone Run Commands on Your Server

A maximum-severity bug in the open-source Ruflo tool, used with Claude Code and Codex, scores a perfect 10.0 and requires no login to exploit.

3 min read
An AI agent with multiple oversized keys floating around it, each granting access to different company systems, with security researchers observing from the sid
Identity & Access

AI agents with too many keys: why permissions are the new identity problem

As companies rush to deploy AI assistants that act on their behalf, security researchers warn the real danger is not the AI itself but the sweeping access rights it inherits.

4 min read
A modern cybersecurity operations center being replaced by an AI platform interface displaying network traffic patterns learning and adapting after each detecte
AI Security

Mate Security Pulls In $35 Million to Build an AI-Powered Cyber Defence System That Learns on the Job

The Tel Aviv startup wants to replace traditional security operations centres with an AI platform that studies each company's own network and gets smarter after every attack it handles.

3 min read
A security analyst's desk cluttered with multiple monitors displaying cascading code and vulnerability alerts in real-time, with one screen showing a timeline c
Opinion

AI Is Shrinking the Time Between Bug and Break-In. Playbooks Haven't Caught Up.

Vendors are pitching AI-driven vulnerability tools like Mythos as the answer. The harder question is what defenders have been doing wrong for years.

4 min read
A government office desk with federal compliance documents and updated patch management timelines, an AI-generated threat assessment report beside them, represe
Policy & Regulation

The US Government Just Changed How Agencies Must Fix Security Flaws. It Is Not Enough.

A new federal directive finally ties patch deadlines to real-world risk. Then AI rewrote the problem.

5 min read
© 2026 Threat Vectr