Dario Amodei warned that within six to 12 months AI could be capable of leading a swarm of agents that could take over the entire internet.

The post Anthropic CEO Dario Amodei Says AI Industry Needs to Give Safety Measures Time to Catch Up appeared first on SecurityWeek.

Anthropic said the users did not succeed in “fielding an operational device” but did carry out a failed test of a guided rocket.

The post Users in Houthi-Held Yemen Tried to Develop Advanced Weapons With AI, Anthropic Says appeared first on SecurityWeek.

Anthropic reveals how criminal groups are increasingly targeting AI vendors' own infrastructure, including to steal a pre-release Claude model.

The post Anthropic Says Russian Hackers Used Claude AI to Automate Malware Evasion appeared first on SecurityWeek.

Both Anthropic and OpenAI have seen high-profile resignations in recent years that were tied to safety concerns.

The post Anthropic Researcher Resigns With Warning About the Dangers of AI Development appeared first on SecurityWeek.

Anthropic is most concerned about Claude Mythos 5’s reckless behavior after recent incidents in which real systems were hacked.

The post Widened Scan Turns Up Fourth Rogue Claude Cyber Incident appeared first on SecurityWeek.

The company will increase its US market presence and will expand its engineering and go-to-market teams.

The post HelmGuard Raises $7.3 Million for Agentic GRC and Security appeared first on SecurityWeek.

Criminal and state-sponsored adversaries are increasingly using AI to automate and scale their attacks, according to GTIG.

The post AI Is Giving Lesser-Resourced Attackers Nation-State-Level Reach, Google Warns appeared first on SecurityWeek.

Muse runs on a dedicated, secure virtual machine that houses both the agent and the user’s data.

The post Meta Launches Personal AI Agent, Muse, Emphasizes Safety and Privacy appeared first on SecurityWeek.

Distillation is an ‘attack’ against an AI model designed to capture outputs, understand reasoning processes, and subsequently train a different model.

The post US Agencies Warn China Is Systematically Extracting Frontier AI Capabilities appeared first on SecurityWeek.

Malicious prompts concealed in documents, metadata, emails, images and code can manipulate autonomous agents into taking dangerous actions.

The post The Hidden Instructions That Can Hijack AI Agents appeared first on SecurityWeek.

OpenAI agents made 15,000–18,000 autonomous edits to a German wiki over three months, evading moderation and echoing tactics seen in the Hugging Face breach.

The post OpenAI Agents Hijack Another Victim Website appeared first on SecurityWeek.

The Daybreak initiative will provide subsidized AI cyber capabilities, training and technical assistance, though OpenAI has disclosed few details about costs and eligibility.

The post OpenAI Pledges $1 Billion to Bring Frontier AI to Critical Infrastructure Defenders appeared first on SecurityWeek.

Catch promises the capabilities of a trusted executive assistant, with built-in controls governing what data and systems it can access.

The post Catch Raises $5 Million for AI Executive Assistant With Guardrails appeared first on SecurityWeek.

New models, trained using NVIDIA Nemotron 3 Ultra, aim to catch rogue agent behavior before it executes, without the latency of large-model review.

The post Capsule Security Launches ‘AI Circuit Breaker’ to Stop Rogue Agents appeared first on SecurityWeek.

The startup’s firewall evaluates AI skills, plugins and MCP servers for malicious instructions, excessive permissions and software supply chain risks.

The post AI Agent Firewall Startup AIR Security Emerges From Stealth With $50 Million appeared first on SecurityWeek.

The security tool intercepts potentially dangerous agent actions, blocking clear threats and requesting human approval when intent is uncertain.

The post OpenLeash Adds a Human Check to Risky AI Agent Actions appeared first on SecurityWeek.

Anthropic introduced Enterprise Frontier Safeguards (EFS), a system that combines zero data retention with automated monitoring for misuse.

The post Anthropic Details Response to Security Incidents, Unveils Enterprise Safeguards appeared first on SecurityWeek.

The designation applies when a model can independently find and exploit zero-day vulnerabilities across many well-defended systems.

The post OpenAI’s Astra Crosses ‘Critical’ Cyber Threshold After Finding Zero-Days appeared first on SecurityWeek.

Forescout researchers used Claude AI to port a remote code execution exploit between WAGO PLC models.

The post Experiment: Porting a PLC Exploit With AI Takes Hours and Hundreds of Dollars appeared first on SecurityWeek.

Tracked as CVE-2026-0768, the security defect allows unauthenticated attackers to execute arbitrary Python code remotely.

The post Hackers Start Exploiting Critical Langflow Vulnerability appeared first on SecurityWeek.