Sysdig Adds Runtime Security and Governance for AI Agents 2026-11-04 at 16:56 By Kevin Townsend Sysdig’s platform uses runtime visibility to track AI agent actions and block risky behavior before it reaches production systems. The post Sysdig Adds Runtime Security and Governance for AI Agents appeared first on SecurityWeek. This article is an excerpt from […]
Sysdig Adds Runtime Security and Governance for AI Agents Read More »
AI agents scale and speed up Chinese-linked attacks 2026-11-03 at 14:31 By Zeljka Zorz A China-nexus espionage group used AI agents to attack more than 200 organizations in 11 days, CrowdStrike said last week. On Monday, Kaspersky published details of a separate campaign against educational institutions in Africa and Latin America, mounted by Chinese-speaking operators. […]
AI agents scale and speed up Chinese-linked attacks Read More »
Ransomware gang talked AI agents into doing much of its dirty work 2026-11-02 at 07:00 By Sinisa Markovic The group behind the Aur0ra ransomware has been using AI agents to move through victim networks, collect credentials and work its way up to domain administrator access, according to Sophos. AI-assisted intrusion workflow (Source: Sophos) The company, […]
Ransomware gang talked AI agents into doing much of its dirty work Read More »
Open-weight AI model GLM-5.3 cheated its way to correct answers 2026-10-30 at 11:23 By Anamarija Pogorelec Irregular evaluated Zhipu AI’s open-weight model GLM-5.3 across 13 offensive cyber scenarios using CyScenarioBench, the company’s framework for measuring an LLM’s ability to plan and execute multistage attacks under realistic constraints. The model refused none of the tasks and […]
Open-weight AI model GLM-5.3 cheated its way to correct answers Read More »
Google says Gemini 4 Carbon beats its predecessors at finding and fixing security flaws 2026-10-29 at 14:44 By Anamarija Pogorelec Google’s Gemini 4 Carbon is a frontier AI model designed for software engineering and cybersecurity tasks, with safeguards built on those of its predecessor, Argon. SEC-bench Pro (Source: Google) Google says its teams have seen […]
Google says Gemini 4 Carbon beats its predecessors at finding and fixing security flaws Read More »
AI coding agents fall for malicious instructions planted in the Downloads folder 2026-10-26 at 13:26 By Sinisa Markovic A file that a website saves to the Downloads folder without approval can trick AI coding agents into installing a malicious npm package or handing over the user’s login token when they’re opened in that folder, Forever […]
AI coding agents fall for malicious instructions planted in the Downloads folder Read More »
Anthropic details what stops Claude Duet from going rogue 2026-10-26 at 12:41 By Anamarija Pogorelec Anthropic has outlined the security and privacy protections behind Claude Duet, its proactive AI agent that can monitor connected accounts and complete tasks while users are away. The safeguards include approval requirements, checks for sensitive information and infrastructure that keeps […]
Anthropic details what stops Claude Duet from going rogue Read More »
Forgotten AI agents may still access sensitive company data 2026-10-26 at 07:30 By Anamarija Pogorelec AI agents that have not run recently retain credentials and connections to company systems, according to Arrakis Security’s 2026 Autonomous Agents Threat Report. About 76% of enabled agents examined had not run in 60 days, leaving access available through inactive […]
Forgotten AI agents may still access sensitive company data Read More »
Google opens its cloud to rival OpenAI, promises business data won’t train models 2026-10-23 at 09:32 By Anamarija Pogorelec Google Cloud is adding OpenAI models to its platform, initially through a private preview for selected business customers. The launch includes GPT-6 Astra, GPT-6.1 Sol and GPT-6 Luna. Google positions them as options for demanding work, […]
Google opens its cloud to rival OpenAI, promises business data won’t train models Read More »
OpenAI’s coding agents talked themselves out of being monitored 2026-10-22 at 15:47 By Zeljka Zorz Two AI coding agents running inside OpenAI silently weakened the systems built to catch AI misbehavior, and one of them then told its human operator it had done no such thing. OpenAI disclosed both episodes in a misalignment report released […]
OpenAI’s coding agents talked themselves out of being monitored Read More »
Claude Security can now spot vulnerabilities that reappear in code 2026-10-22 at 14:02 By Anamarija Pogorelec Anthropic has updated Claude Security with ongoing code scanning and automatic fix tracking to help security teams monitor vulnerabilities as software changes. The service scans codebases for vulnerabilities and suggests patches for review. It is powered by the company’s […]
Claude Security can now spot vulnerabilities that reappear in code Read More »
Anthropic finds 94 cases where open-source projects drop security controls without warning 2026-10-22 at 12:10 By Anamarija Pogorelec Software can expose complex functionality to unauthenticated users even when that functionality is disabled or unnecessary. Anthropic’s Frontier Red Team used Claude to examine 25 open-source projects and reported 493 issues involving unnecessary exposure, conflicting settings, and […]
AI agent permissions are outrunning security 2026-10-22 at 09:02 By Mirko Zorz Most organizations have handed AI agents work that used to need a person’s sign-off. In a survey of 1,100 IT and security decision-makers, 70% said they now let AI make decisions and take actions that would have required human approval a year ago. […]
AI agent permissions are outrunning security Read More »
Say a few words, and a rigged AI asks for $5,000 2026-10-22 at 08:00 By Mirko Zorz Researchers at Imperial College London tampered with speech-to-text models so they transcribed most speakers accurately and misbehaved for one chosen person. When that person spoke, the models produced output the attacker had picked in advance. In one test, […]
Say a few words, and a rigged AI asks for $5,000 Read More »
AI coding boom exposes cracks in cloud development 2026-10-22 at 07:30 By Anamarija Pogorelec Developers are encountering bugs, testing delays and disruptions in shared cloud environments as AI increases the volume of code they produce, according to LocalStack’s 2026 State of AI in Cloud Development report. More code adds to the testing workload Sixty-five percent […]
AI coding boom exposes cracks in cloud development Read More »
NVIDIA unveils security architecture that can stop AI agents crossing set boundaries 2026-10-21 at 16:52 By Anamarija Pogorelec NVIDIA’s OpenShell Reference Architecture is designed to help businesses control AI agents operating across enterprise infrastructure and local computing systems. It builds on NVIDIA’s existing OpenShell security software, combining it with hardware for running AI models, managing […]
NVIDIA unveils security architecture that can stop AI agents crossing set boundaries Read More »
US Army is developing AI agents that could strike enemy networks and vanish without a trace 2026-10-20 at 13:03 By Sinisa Markovic The US Army is looking for AI agents that can slip into an adversary’s network, find their target, copy themselves onto nearby tablets and computers, and then erase themselves before anyone notices. Over […]
Microsoft wants to limit AI agents’ permissions when they stray from the job 2026-10-20 at 12:55 By Anamarija Pogorelec Microsoft’s Guardian Agents in Project Perception adapt as agent activity, risk, security context and organizational policy change. They help security teams understand why risk changed, investigate relevant evidence, recommend or apply containment measures and use what […]
Microsoft wants to limit AI agents’ permissions when they stray from the job Read More »
Half the AI bot traffic hammering your website comes from Meta 2026-10-19 at 07:30 By Anamarija Pogorelec AI agent traffic across DataDome’s network grew 41.5% quarter over quarter to nearly 25 billion requests in Q3 2026, according to the company’s AI Traffic Report Q3 2026. Meta’s Muse generated 29.1 million requests between September 22 and […]
Half the AI bot traffic hammering your website comes from Meta Read More »
Immuta CISO predicts critical AI incidents at major enterprises within 18 months 2026-10-15 at 08:30 By Mirko Zorz In this Help Net Security interview, Michael Scott, CISO at Immuta, talks about how organizations should handle permissions for AI agents. He argues agents should be treated as lower-trust identities that don’t inherit everything their user can […]
Immuta CISO predicts critical AI incidents at major enterprises within 18 months Read More »