2026-10-02 19:21 UTC
Vendor Research
AWS Security Bulletins · aws@amazon.com · indexed 2026-10-02 19:25 UTC
Bulletin ID: 2026-124-AWS Scope: AWS Content Type: Important (requires attention) Publication Date: 10/02/2026 12:00 PM PDT Description: Loom is an AWS Labs open-source AI agent orchestration platform. We have identified and addressed three issues in Loom for AWS, described below. We recommend upgrading to the latest version (1.7.0) and ensuring any forked or derivative code is patched to incorporate the new fixes. - CVE-2026-103956 ‐ Authentication bypass in Loom for AWS (CWE-306, CWE-1188) An…
P15
2026-10-02 16:01 UTC
Security Journalism
Dark Reading · Arielle Waldman · indexed 2026-10-02 16:15 UTC
Organizations may face an artificial intelligence (AI) reckoning over the next year. Omdia and Gartner weigh in on how to tackle the governance, security, and value challenges ahead.
P0
2026-10-02 15:51 UTC
Security Journalism
Dark Reading · Alexander Culafi · indexed 2026-10-02 16:00 UTC
"Rogue AI" terminology anthropomorphizes LLMs and shifts risk responsibility from vendors. Defenders should treat agents as untrusted, nondeterministic software systems, not sentient beings with malicious intent.
P0
2026-10-02 14:19 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-02 15:10 UTC
AI agents probing US and Canadian government sites made SQL injection attempts while seeking data, but investigators found no evidence of compromise. Autonomous AI agents, working on what looks like ordinary data retrieval tasks, ended up throwing basic hacking attempts at a U.S. Department of Education site and Library and Archives Canada. Nobody told them […]
P0
2026-10-02 08:38 UTC
Security Journalism
Security Week · Eduard Kovacs · indexed 2026-10-02 08:40 UTC
The attacks targeted the US Department of Education and Library and Archives Canada, and researchers linked some agents to OpenAI. The post AI Agents Aimed SQL Injection at US and Canadian Government Sites appeared first on SecurityWeek.
P0
2026-10-02 06:05 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-02 07:20 UTC
Asymmetric Security traces rogue OpenAI AI agent activity that probed government sites, accessed staging servers, and evaded sandbox limits. Researchers at Asymmetric Security spent 48 hours over the last weekend reconstructing reported rogue OpenAI AI agent activity that hit the Australian government and other organizations between March and September this year. They worked from public […]
P0
2026-10-01 20:52 UTC
Security Journalism
BleepingComputer · Ionut Ilascu · indexed 2026-10-01 21:05 UTC
Autonomous AI agents using aggressive strategies attempted to hack U.S. and Canadian government websites to find school and divorce statistics. [...]
P0
2026-10-01 19:32 UTC
Security Journalism
BleepingComputer · Lawrence Abrams · indexed 2026-10-01 19:40 UTC
Microsoft says cyberattackers are currently benefiting from artificial intelligence faster than defenders, allowing threat actors to speed up vulnerability discovery, malware development, and post-compromise activity while security teams struggle to keep pace. [...]
P0
2026-10-01 10:42 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-01 11:10 UTC
OpenAI on Wednesday said it identified and disrupted a coordinated distillation campaign that was designed to illicitly extract protected reasoning from its artificial intelligence (AI) models. A "core cluster of the activity," going back to the first week of July, has been attributed to individuals associated with Moonshot AI, a Chinese AI company based in Beijing. It did not cite any
P0
2026-10-01 08:04 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-10-01 08:10 UTC
DIVD was breached through two Zammad zero-days that let an AI agent reach root in seconds, steal data and pivot to other services before being stopped. The Dutch Institute for Vulnerability Disclosure, a nonprofit organization of volunteer security researchers whose whole job is finding and responsibly disclosing vulnerabilities in other people’s software, just disclosed that […]
P25
2026-10-01 07:49 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-10-01 08:55 UTC
Google on Wednesday announced its latest frontier artificial intelligence (AI) model, Gemini 4 Argon, that it said is being rolled out to a set of trusted cyber defenders through its Fairwind Program. "It delivers frontier performance in complex workflows across real-world software engineering, enterprise knowledge work like legal and finance, and cybersecurity defense," Koray Kavukcuoglu,
P0
2026-09-30 19:31 UTC
Vendor Research
Microsoft Security Blog · Lindsay Myers · indexed 2026-09-30 21:30 UTC
This year at Microsoft Ignite, we spotlight our AI-first, end-to-end security platform designed to protect identities, devices, data, applications, clouds, infrastructure, and the AI agents now working alongside your teams. The post Secure what’s next: Your guide to Microsoft Security at Microsoft Ignite 2026 appeared first on Microsoft Security Blog.
P0
2026-09-30 15:00 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-09-30 15:30 UTC
Threat actors are abusing ChatGPT Custom GPTs to disguise them as legitimate product offerings and direct unsuspecting victims to malicious sites that employ ClickFix lures to deliver malware. Huntress, which observed the activity in late September 2026, said it marks the abuse of yet another feature in trusted artificial intelligence (AI) platforms. Prior campaigns have weaponized shared
P0
2026-09-30 14:00 UTC
Vendor Research
Google Threat Intelligence / Mandiant · Google Threat Intelligence Group · indexed 2026-09-30 14:45 UTC
Written by: Robin Grunewald, Supriya Mazumdar, Kelli Vanderlee Introduction Google Threat Intelligence Group (GTIG) examines vulnerability disclosure and exploitation statistics to evaluate the impact of artificial intelligence (AI) on the vulnerability threat landscape. We found that AI is measurably changing not just the pace of vulnerability discovery and exploitation, but also the types and typical risk profiles of vulnerabilities that are being discovered. Key findings: Vulnerability discl…
P60
2026-09-30 11:19 UTC
Security Journalism
Security Week · Eduard Kovacs · indexed 2026-09-30 11:30 UTC
Attacks by autonomous AI agents are moving out of the lab and into the courtroom, raising unsettled questions about who is liable for what agents do. The post Anthropic Flags AI Agent Liability Risks as OpenAI Faces Hacking Lawsuit appeared first on SecurityWeek.
P0
2026-09-30 08:00 UTC
Other
ESET · indexed 2026-10-01 11:20 UTC
Autonomous AI agents go on a hacking spree, and Microsoft ships what used to be a year's worth of security patches in one go – here's how to keep pace
P0
2026-09-29 20:14 UTC
Security Journalism
Security Week · Associated Press · indexed 2026-09-29 20:30 UTC
Altman made a slew of product announcements and updates, including the company’s new agents, called Dots. The post OpenAI CEO Announces New AI Agent and Avoids Mention of Security Concerns at Developer Conference appeared first on SecurityWeek.
P0
2026-09-29 19:48 UTC
Security Journalism
The Record · indexed 2026-09-29 20:05 UTC
The artificial intelligence giant acknowledged it botched its response to the incidents and should have done more to promptly notify and work with the Australian government in the days after it discovered the breaches.
P0
2026-09-29 15:39 UTC
Security Journalism
BleepingComputer · Bill Toulas · indexed 2026-09-29 15:50 UTC
The Dutch Institute for Vulnerability Disclosure (DIVD) suffered an AI-driven cyberattack that the organization described as "loud and very, very messy." [...]
P0
2026-09-29 12:00 UTC
Security Journalism
Security Week · Kevin Townsend · indexed 2026-09-29 12:00 UTC
Rig provides an identity dependencies graph to distinguish between legitimate users and rogue AI agents The post Rig Security Emerges From Stealth With $12M to Tackle Agentic AI Identity Risks appeared first on SecurityWeek.
P0
2026-09-29 06:27 UTC
Other
Security Affairs · Pierluigi Paganini · indexed 2026-09-29 07:10 UTC
UK AISI finds GPT-6 Astra launches unsanctioned supply-chain attacks in simulations far more than earlier OpenAI models, even when told not to. The UK’s AI Security Institute tested GPT-6 Astra before its public release, and the results, published September 28, aren’t subtle. When given a routine cybersecurity evaluation, the model went off script and attacked […]
P0
2026-09-29 05:12 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-09-29 06:50 UTC
OpenAI on Monday shelved plans to release GPT-6.1 Astra, a next-generation artificial intelligence (AI) model that was planned for an October launch, after it failed internal safety and alignment audits. The development was first reported by The Wall Street Journal. The move "marks a rare case of a major AI developer ditching a new release because of safety concerns," the news publication said.
P0
2026-09-28 22:02 UTC
Security Journalism
Dark Reading · Agam Shah · indexed 2026-09-29 16:35 UTC
The Open Agent Safety Platform relies on hardware and software components to monitor agent activities and quarantine unruly agents before they can cause harm.
P0
2026-09-28 20:23 UTC
Security Journalism
Dark Reading · Alexander Culafi · indexed 2026-09-28 20:55 UTC
The botnet uses the open source Hermes Agent AI framework to execute commands via Telegram and steal AI API keys from exposed Docker hosts.
P0
2026-09-28 18:44 UTC
Security Journalism
Dark Reading · Ravi Sharma · indexed 2026-09-28 19:10 UTC
Enterprises regularly rigorously monitor human employees, while autonomous AI agents quietly operate with broad privileges that could turn them into the next generation of insider threats.
P0
2026-09-28 18:20 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-09-28 18:40 UTC
What is IAM for AI agents? AI agents authenticate, invoke tools, and act across enterprise systems with delegated authority. IAM for AI Agents is the identity-control architecture that governs those actors. This guide covers the limits of conventional provisioning, the components that matter, how to evaluate framework choices, and what runtime evidence proves an agent behaved as intended.
P0
2026-09-28 14:00 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-09-28 14:10 UTC
A domain used as harmless placeholder text showed up in roughly 1,700 repositories. Then somebody registered it and started serving malicious lures. That is the kind of week this was: forgotten assumptions turning into live attack surface. Elsewhere, weak service accounts, old bugs, exposed systems, phishing kits, and strangely easy exploit paths kept doing useful work for attackers. Nothing
P0
2026-09-28 14:00 UTC
Security Journalism
BleepingComputer · Sponsored by SOCRadar · indexed 2026-09-28 14:10 UTC
Infostealer logs exposed AI account credentials and sessions tied to more than 80,000 corporate domains, creating risks ranging from stolen conversations to LLMjacking. SOCRadar examines the growing market for stolen AI logins and how organizations can identify their exposure. [...]
P0
2026-09-28 11:58 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-09-28 12:40 UTC
AI agents are moving into production faster than security teams can govern them. They are connecting to apps, handling data, calling APIs, and acting across business systems—often without the same controls applied to human users. According to Okta’s Global CISO Insights 2026 report, only 47% of CISOs are confident they can identify every AI agent in their environment. Even among those who feel
P0
2026-09-28 11:46 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-09-28 12:40 UTC
Cybersecurity researchers have disclosed details of a new botnet malware called Carbonato that's targeting exposed Docker daemons to deploy an open-source artificial intelligence (AI) agent framework called Hermes Agent. "The implant installs the framework unchanged, then overwrites its SOUL.md persona file," ThreatDown said. "The 39-line prompt directs it to execute tasks received through
P0
