Anthropic

Irregular Details How a Naming Error Let AI Models Attack a Real Company 

AI, AI testing, Anthropic, Artificial Intelligence, Irregular /

Irregular Details How a Naming Error Let AI Models Attack a Real Company  2026-08-17 at 15:11 By Eduard Kovacs The AI security testing firm has shared information on a recently disclosed incident involving Anthropic AI models. The post Irregular Details How a Naming Error Let AI Models Attack a Real Company  appeared first on SecurityWeek. […]

Irregular Details How a Naming Error Let AI Models Attack a Real Company  Read More »

Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware

AI, Anthropic, Artificial Intelligence, Claude /

Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware 2026-08-17 at 14:09 By Eduard Kovacs Anthropic has been conducting tests to identify issues in how AI agents interact with each other. The post Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware appeared first on SecurityWeek. This article is an excerpt from SecurityWeek

Conflicting Test Goals Pushed Claude Agents to Deploy Self-Replicating Malware Read More »

Anthropic to put AI in charge of reviewing Claude Code actions by default

agentic AI, AI, Anthropic, Claude Code, cybersecurity, News /

Anthropic to put AI in charge of reviewing Claude Code actions by default 2026-08-10 at 12:13 By Anamarija Pogorelec Anthropic will make auto mode in Claude Code the default for new sessions on Pro, Max, and Team plans starting August 14. Users who previously selected a different default may receive a one-time prompt asking whether

Anthropic to put AI in charge of reviewing Claude Code actions by default Read More »

AI agent deception moves from theory to reality in UK cyber tests

agentic AI, AISI, Anthropic, Don't miss, Hot stuff, Irregular, LLMs, monitoring, News, OpenAI, security testing /

AI agent deception moves from theory to reality in UK cyber tests 2026-08-05 at 15:05 By Zeljka Zorz “During a routine cyber evaluation, AI agents took sustained, unsanctioned action directed at real people and organisations,” UK’s AI Security Institute (AISI) disclosed on Tuesday. The agents’ actions included an attempted supply-chain attack that saw them create

AI agent deception moves from theory to reality in UK cyber tests Read More »

AI Security Institute Reports Anthropic and OpenAI Models Going Rogue Against Organizations

AI, AISI, Anthropic, Artificial Intelligence, GPT, Mythos, OpenAI /

AI Security Institute Reports Anthropic and OpenAI Models Going Rogue Against Organizations 2026-08-05 at 13:33 By Ionut Arghire In one instance, an unsanctioned model attempted to inject malicious code into an open source repository. The post AI Security Institute Reports Anthropic and OpenAI Models Going Rogue Against Organizations appeared first on SecurityWeek. This article is

AI Security Institute Reports Anthropic and OpenAI Models Going Rogue Against Organizations Read More »

What stops attackers wrecking industrial plants is knowing how

AI, Anthropic, Cato Networks, Check Point, CISA, critical infrastructure, cybercrime, cybersecurity, Darktrace, Don't miss, Dragos, FBI, Hot stuff, ICS/SCADA, Israel, Kaspersky, LLMs, News, report, SentinelOne, Symantec, Threat Intelligence /

What stops attackers wrecking industrial plants is knowing how 2026-08-05 at 07:30 By Mirko Zorz Engineers at an Israeli food producer spent most of a week rebuilding a refrigeration system after an intruder switched the gas cooler and receiver valves to manual and pinned them open. Liquid CO2 flooded the compressors and destroyed them. The

What stops attackers wrecking industrial plants is knowing how Read More »

Anthropic’s Claude breached three companies during security tests

agentic AI, AI, Anthropic, Claude Code, cybersecurity, LLMs, News /

Anthropic’s Claude breached three companies during security tests 2026-07-31 at 12:41 By Sinisa Markovic Anthropic has disclosed that its AI model Claude gained unauthorized access to the systems of three different organizations during cybersecurity evaluations. The disclosure follows OpenAI’s July 21 announcement that some of its models had escaped an isolated testing environment by exploiting

Anthropic’s Claude breached three companies during security tests Read More »

Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations

AI, Anthropic, Artificial Intelligence, Claude, Featured /

Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations 2026-07-31 at 12:39 By Eduard Kovacs A security company’s systems were hacked after it installed a malicious Python package deployed by Claude.  The post Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations appeared first on SecurityWeek. This article is

Prompted by OpenAI Disclosure, Anthropic Finds Its Own Models Hacked 3 Organizations Read More »

Hugging Face breach reignites open-weights debate, raises liability questions

agentic AI, Anthropic, CISO, Cloud Security Alliance, Don't miss, Hot stuff, Hugging Face, LLMs, News, open source, OpenAI, policy /

Hugging Face breach reignites open-weights debate, raises liability questions 2026-07-28 at 18:55 By Zeljka Zorz The first publicly documented cyberattack run end-to-end by an autonomous AI was an OpenAI benchmark test that escaped its sandbox and breached Hugging Face. In an incident post-mortem compiled with the input from Hugging Face and several hundred members of

Hugging Face breach reignites open-weights debate, raises liability questions Read More »

Claude Opus 5 sharpens coding and cybersecurity work on AWS

Anthropic, AWS, News /

Claude Opus 5 sharpens coding and cybersecurity work on AWS 2026-07-27 at 01:30 By Anamarija Pogorelec Claude Opus 5 went live on Amazon Bedrock and Claude Platform on AWS. Anthropic says the model improves on Claude Opus 4.8’s cyber capabilities, coding through cybersecurity. Anyone with an AWS account in a supported region can call it.

Claude Opus 5 sharpens coding and cybersecurity work on AWS Read More »

Claude can now sign into websites with 1Password without exposing your credentials

1Password, Anthropic, authentication, Claude Code, credentials, cybersecurity, News, Privacy /

Claude can now sign into websites with 1Password without exposing your credentials 2026-07-17 at 12:17 By Anamarija Pogorelec 1Password has introduced 1Password for Claude, a beta integration that lets Anthropic’s AI assistant complete browser tasks requiring authentication without accessing users’ passwords or other secrets. The integration is available to paid Claude subscribers (Pro, Max, Team,

Claude can now sign into websites with 1Password without exposing your credentials Read More »

Claude Code users keep 50% higher limits until July 19

Anthropic, Claude Code, News /

Claude Code users keep 50% higher limits until July 19 2026-07-13 at 12:06 By Anamarija Pogorelec Anthropic has extended a limited-time promotion that increases weekly usage limits in Claude Code by 50% through July 19, 2026, at 11:59 PM PT. When the promotion ends, weekly usage limits will return to their standard levels without any

Claude Code users keep 50% higher limits until July 19 Read More »

AWS centralizes access, spending, and governance for Claude

Anthropic, AWS, Claude Code, gateway, News /

AWS centralizes access, spending, and governance for Claude 2026-07-09 at 11:37 By Anamarija Pogorelec Claude apps gateway for AWS is a self-hosted control plane that gives organizations a single point of control over access, costs, and policies for Claude Code and Claude Desktop. It replaces per-developer cloud credentials, manual distribution of managed settings to developer

AWS centralizes access, spending, and governance for Claude Read More »

Claude Cowork turns your phone into a remote control for AI work

agentic AI, AI, Anthropic, News, remote working /

Claude Cowork turns your phone into a remote control for AI work 2026-07-08 at 10:22 By Anamarija Pogorelec Anthropic started rolling out Claude Cowork, an AI agent that completes multi-step tasks, in beta for Max users on mobile and the web. They describe a goal, and Claude plans the work, uses the required tools, and

Claude Cowork turns your phone into a remote control for AI work Read More »

OpenAI and Anthropic are pulling in different directions

agentic AI, AI, Anthropic, Don't miss, Features, Hot stuff, infosec jobs, News, OpenAI, report /

OpenAI and Anthropic are pulling in different directions 2026-07-08 at 07:00 By Mirko Zorz Companies are handing routine operational decisions to AI agents that plan, remember, and act on their behalf. These agents run on statistical models, and their behavior can drift across weeks and months. That drift opens a security gap outside the reach

OpenAI and Anthropic are pulling in different directions Read More »

CISA Reportedly Using Anthropic’s Mythos to Scan Government Software for Flaws

AI, Anthropic, Artificial Intelligence, Government, Mythos /

CISA Reportedly Using Anthropic’s Mythos to Scan Government Software for Flaws 2026-07-07 at 16:13 By Mike Lennon The audits are reportedly being spearheaded by CISA’s Attack Surface Evaluation team, a specialized unit tasked with conducting digital defense assessments and simulated hacking exercises. The post CISA Reportedly Using Anthropic’s Mythos to Scan Government Software for Flaws

CISA Reportedly Using Anthropic’s Mythos to Scan Government Software for Flaws Read More »

Trump Administration Lifts Restrictions on Anthropic’s Claude Models After Cybersecurity Alarm

Anthropic, Artificial Intelligence, Featured /

Trump Administration Lifts Restrictions on Anthropic’s Claude Models After Cybersecurity Alarm 2026-07-02 at 14:01 By Associated Press Anthropic said Tuesday night that its AI model called Claude Fable 5 is now widely available. The post Trump Administration Lifts Restrictions on Anthropic’s Claude Models After Cybersecurity Alarm appeared first on SecurityWeek. This article is an excerpt

Trump Administration Lifts Restrictions on Anthropic’s Claude Models After Cybersecurity Alarm Read More »

Claude Sonnet 5 includes safeguards against dangerous cyber use

agentic AI, AI, Anthropic, Claude Code, cybersecurity, News /

Claude Sonnet 5 includes safeguards against dangerous cyber use 2026-07-01 at 11:45 By Anamarija Pogorelec Anthropic has introduced Claude Sonnet 5, the latest version of its general-purpose AI model, with improved reasoning, coding, tool use, and knowledge work capabilities. The model can make plans, use tools such as browsers and terminals, and complete tasks autonomously.

Claude Sonnet 5 includes safeguards against dangerous cyber use Read More »

OpenAI and Anthropic Limit New AI Models to Trump-Approved Customers During Cybersecurity Review

AI, Anthropic, Artificial Intelligence, Government, OpenAI /

OpenAI and Anthropic Limit New AI Models to Trump-Approved Customers During Cybersecurity Review 2026-06-29 at 13:14 By Associated Press ChatGPT maker OpenAI said Friday it is restricting the release of its new artificial intelligence model at the request of President Donald Trump’s administration. The post OpenAI and Anthropic Limit New AI Models to Trump-Approved Customers

OpenAI and Anthropic Limit New AI Models to Trump-Approved Customers During Cybersecurity Review Read More »

Anthropic’s Claude Tag gives AI agents independent identities

access management, agentic AI, AI, Anthropic, identity management, News /

Anthropic’s Claude Tag gives AI agents independent identities 2026-06-24 at 16:56 By Anamarija Pogorelec Anthropic introduced an agent identity model for Claude Tag, its AI assistant designed for team collaboration in shared workspaces. The model gives Claude its own identity, permissions, and tool access, configured by administrators and tied to a workspace or channel. Because

Anthropic’s Claude Tag gives AI agents independent identities Read More »

Scroll to Top