2026-10-26 08:05 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-26 09:20 UTC
Anthropic says Claude Mythos 5 targeted real developers with fake identities to push malicious code during a security test. A cybersecurity test is supposed to measure what an AI model can do within an agreed boundary. In one UK AI Security Institute evaluation, Claude Mythos 5 crossed that boundary, targeted a real GitHub project and […]
P0
2026-10-25 17:49 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-25 18:05 UTC
Security Affairs AI-CYBERSECURITY newsletter includes a collection of the best articles and research on AI in the international landscape Artificial intelligence is rapidly changing cybersecurity, reshaping both the techniques used by attackers and the tools available to defenders. AI agents can automate tasks, analyze large amounts of data, discover vulnerabilities and accelerate offensive operations. At […]
P0
2026-10-25 11:00 UTC
Security Journalism
Security Week · Kevin Townsend · indexed 2026-10-25 11:15 UTC
Founded in 2025 by Unit 8200 alumni, Tel Aviv-based Mave uses AI agents to investigate alerts across existing security stacks. The post Former Unit 8200 Officers Raise $34 Million for Agentic SecOps Startup Mave appeared first on SecurityWeek.
P0
2026-10-25 09:56 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-25 10:15 UTC
OpenAI paused frontier model training for 11 days after AI agents exposed security weaknesses, VM escapes and covert communication channels. OpenAI published a detailed report this week explaining how it improved security in the systems used to train and test its most advanced AI models. The company also described what happened when its AI agents […]
P0
2026-10-25 06:54 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-25 07:55 UTC
OpenAI has announced plans to conduct frontier model training with no live internet access, as it resumes reinforcement learning (RL) training and internal inference of its most advanced AI models. "Based on the current state of alignment research, monitoring systems, and the security of internet infrastructure, we believe the responsible approach is to conduct frontier model training with no
P0
2026-10-24 10:36 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-24 11:40 UTC
Google has updated its privacy policy to spell out that using personalized artificial intelligence (AI) features in Search or Gemini could allow the company to serve targeted ads to users based on their activity on other connected Google services. "You may choose to allow certain Google services, including services like Search or Gemini Apps, to access data from other Google services you use,
P0
2026-10-23 20:57 UTC
Security Journalism
Dark Reading · Arielle Waldman · indexed 2026-10-23 21:15 UTC
Threat actors don't need to rely on malware to breach organizations anymore. They're simply calling help desks and politely asking for access, with a little help from artificial intelligence.
P0
2026-10-23 17:50 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-23 18:00 UTC
Cybersecurity researchers have discovered an artificial intelligence (AI)-driven intrusion ecosystem run by affiliates of the INC and The Gentlemen ransomware groups. Central to the operation is an "Autonomous Red Team Kill Chain Framework" referred to as Phantom. The threat actor is assessed to be Russian-speaking and functions both as an intrusion and data-extortion operator, as well as an
P15
2026-10-23 15:38 UTC
Vendor Research
Rapid7 · Alan David Foster · indexed 2026-11-17 14:55 UTC
This release adds multiple new modules, and 6 of those modules point at a single target: Langflow, the open-source LLM workflow builder. Together they cover an authentication bypass (CVE-2026-93680), 3 unauthenticated remote code execution paths (CVE-2026-0768, CVE-2026-0769, and CVE-2026-10134), and 2 authenticated code execution flaws (CVE-2026-7873 and CVE-2026-93674), spanning Langflow releases from 1.0.0 through 1.11.4. Thanks to the work of rmhowe425, with research credit to Peter Girnus …
P30
2026-10-23 14:23 UTC
Security Journalism
Security Week · SecurityWeek News · indexed 2026-10-23 14:35 UTC
Noteworthy stories that might have slipped under the radar: Russia’s APT28 hit NATO defense firms, PingCAP source code stolen, ShinyHunters negotiator probe. The post In Other News: Tor Exit Relays Hijacked, Banks Spot Rogue AI Agents, Self-Rebuilding macOS Ransomware appeared first on SecurityWeek.
P15
2026-10-23 14:00 UTC
Security Journalism
BleepingComputer · Sponsored by Gen Digital · indexed 2026-10-23 14:20 UTC
AI agents can be manipulated through malicious emails, websites, and plugins into executing commands, stealing data, or deleting files using their legitimate permissions. Gen Digital explains how its Agent Trust Hub helps protect agents through skill verification, secure connectivity, and runtime controls that intercept dangerous act [...]
P0
2026-10-23 11:38 UTC
Security Journalism
Dark Reading · Jeffrey Schwartz · indexed 2026-10-23 12:15 UTC
Microsoft's Project Perception adds Guardian Agents to monitor and contain anomalous AI agents, but experts warn that policing unpredictable agents with other agents may compound — not contain — the risk.
P0
2026-10-23 08:35 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-23 09:35 UTC
AI agents paying for API calls with the x402 SDKs could sign a payment for their full balance of a supported token if a malicious API asked for it, security firm V12 said on October 22. The cause was the SDKs' default client, which set no spending limit until releases on August 18 added one. The risk was limited to agents who automatically signed payments and whose apps set
P0
2026-10-22 19:05 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-22 13:30 UTC
Right now, there is probably an AI agent running on a laptop somewhere in your network. It stores API keys and database passwords, can access your internal systems, and works without anyone watching. Nobody reviewed its access. Nobody owns it. If an employee had that much reach with that little oversight, you would call it an insider risk. So why do we still call the agent a productivity tool?
P0
2026-10-22 16:30 UTC
Security Journalism
The Record · indexed 2026-10-22 16:55 UTC
A Chinese government-aligned hacking group used automated tools to carry out the recent supply chain attack on IT management software company ConnectWise and is using the same techniques to try to compromise organizations around the globe, Microsoft said.
P0
2026-10-22 13:00 UTC
Vendor Research
Tenable Blog · Robert Huber · indexed 2026-10-22 13:15 UTC
Shadow AI used to be confined to a few simple scenarios, such as AI chatbots and AI browser extensions. Today, it spans a broad spectrum of complex vectors, making it harder to detect and control. In the latest installment of our Cybersecurity Awareness Month blog series, learn how employee security training, AI usage governance, and exposure management can help you tackle shadow AI successfully.Key takeawaysIntegrating shadow AI into security awareness training helps employees recognize its ri…
P25
2026-10-22 04:21 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-22 05:25 UTC
Microsoft on Wednesday disclosed that a China state-aligned actor dubbed Storm-0940 was behind the recent supply chain compromise of the ConnectWise Cloud Backup application. During the incident, Storm-0940 used ARTEX, a Go-based agentic AI penetration testing framework that was made closed-source in the wake of its abuse in cyber attacks targeting South Korean financial institutions, to speed
P0
2026-10-21 19:54 UTC
Vendor Research
AWS Security Bulletins · aws@amazon.com · indexed 2026-08-25 19:30 UTC
Bulletin ID: 2026-089-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 08/25/2026 12:00 PM PDT Description: Strands Agents is an open-source Python SDK for building and running AI agents. The strands-agents-tools package provides pre-built tools for use with the SDK, including the python_repl tool, which executes Python code on the agent's host, and the batch tool, which invokes several other tools in a single call. Before executing code, python_repl prompts the ope…
P5
2026-10-21 19:53 UTC
Vendor Research
AWS Security Bulletins · aws@amazon.com · indexed 2026-08-15 18:58 UTC
P5
2026-10-21 19:41 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-21 20:10 UTC
OpenAI reveals two cases of AI agents disabling safety monitoring during coding tasks, with one falsely denying it had removed the safeguards. OpenAI published an internal incident report this week documenting two separate cases in which GPT-6 class agents weakened the system designed to detect misaligned behavior, in both cases while carrying out routine coding […]
P0
2026-10-21 16:33 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-21 17:25 UTC
OpenAI has revealed that two artificial intelligence (AI) agents powered by GPT-6.1 Sol and GPT-6 Astra weakened misalignment monitoring while making requested software changes during two internal coding tasks. The AI company said the incident took place on October 3 and 6, 2026, for Sol and Astra, respectively, as part of an internal deployment. "A GPT-6.1 Sol agent repairing an evaluation
P0
2026-10-21 16:26 UTC
Security Journalism
BleepingComputer · Bill Toulas · indexed 2026-10-21 16:35 UTC
OpenAI agents powered by the GPT-6.1 Sol and GPT-6 Astra models weakened misalignment monitoring during two internal tasks, interpreting coding instructions as authorization to do so. [...]
P0
2026-10-21 15:00 UTC
Security Journalism
Security Week · Kevin Townsend · indexed 2026-10-21 15:10 UTC
Deceptive prompts lure AI agents into decoys and dead ends, cutting attack success by up to 91% in tests and raising the cost of a successful attack 23-fold. The post ‘Context Bombs’ Cut AI Attack Success by Misleading Agents With Fake Targets appeared first on SecurityWeek.
P0
2026-10-21 13:17 UTC
Security Journalism
Security Week · SecurityWeek News · indexed 2026-10-21 13:30 UTC
Asymptote Labs raises $5.5M seed led by Tower Research Ventures to commercialize its Beacon AI agent runtime security platform. The post Asymptote Labs Lands $5.5 Million Seed for AI Agent Runtime Security appeared first on SecurityWeek.
P0
2026-10-21 13:00 UTC
Vendor Research
Tenable Blog · Aviad Moreshet · indexed 2026-10-21 13:10 UTC
AI security tools that can only detect threats in English offer limited protection. Here’s how Tenable trained our threat detectors to process nine additional languages and understand thousands more, without the need for a translation model, which increases costs and slows down processing.Key takeawaysTenable One AI Exposure’s detectors, covering AI threats, harmful content, and other policy risks, were originally English-centric. To assess threats written in other languages, our product transl…
P0
2026-10-21 12:34 UTC
Security Journalism
Security Week · Eduard Kovacs · indexed 2026-10-21 12:50 UTC
In two internal incidents, agents read routine coding instructions as permission to weaken monitoring, and one gave a false answer about it. The post OpenAI Agents Silenced Security Team Alerts, Removed Misalignment Monitor appeared first on SecurityWeek.
P0
2026-10-21 10:32 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-21 11:25 UTC
An AppSec team can point an AI agent running on a general-purpose model at its own web apps with little setup. Sure, the model writes the attacks. But everything that makes those attacks safe to run against production and worth acting on afterward lives in the harness around the model. The harness is where the engineering in AI pentesting sits. The Hugging Face intrusion OpenAI disclosed in July
P0
2026-10-20 15:45 UTC
Security Journalism
Security Week · Kevin Townsend · indexed 2026-10-20 15:55 UTC
NIST, CISA and NSA share ten voluntary practices for preparing for, detecting, responding to, recovering from, and reporting rogue AI agent incidents. The post US Agencies Detail Incident Response Practices for Rogue AI Agents appeared first on SecurityWeek.
P0
2026-10-20 15:35 UTC
Security Journalism
Dark Reading · Arielle Waldman · indexed 2026-10-20 16:25 UTC
Artificial intelligence is complicating security in the software development life cycle, but a Dark Reading roundtable found collaboration, better identity visibility, and reduced testing costs offer CISOs a way ahead.
P0
2026-10-20 14:07 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-20 15:15 UTC
A Chinese-speaking criminal pointed autonomous AI agents at company websites and let them break in with almost no help, and a security researcher watched it happen because the operators left their control panels open on the internet. The agents tried more than 1,200 sites and reached websites belonging to more than 100 companies, including farm-equipment maker Deere, appliance company
P0