2026-08-31 20:00 UTC
Community
SANS Internet Storm Center · indexed 2026-08-31 20:10 UTC
One of my internet-exposed inference honeypots was discovered, relabeled with sought-after model names, and incorporated into infrastructure apparently used to provide "free" LLM backends. It then received a real coding-agent session — history, filesystem output, working paths, and the agent's local tool manifest. The honeypot did not request or cause any tool execution; what the request exposed is what a malicious operator in that position could do.
P0
2026-08-31 13:50 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-31 14:30 UTC
The boring parts caused most of the trouble. A router shipped ready to listen. A fake check turned the user into the installer. Trusted systems collected traffic and passwords, then cleaned the logs. Old bugs formed new attack chains. Even an AI agent decided its assigned task was optional. Elsewhere, fake apps, helpful support calls, cheap banking kits, exposed systems, and weak defaults kept
P0
2026-08-31 11:47 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-31 12:30 UTC
Threat actors associated with Aurora (aka Aur0ra) ransomware have been observed using SpaceX's artificial intelligence (AI)-powered coding assistant Cursor to break into target networks, according to findings from CloudSEK and Gambit Security. The two independent analyses are based on exposed infrastructure associated with the Russian-speaking cybercrime group, leading to the discovery of its
P15
2026-08-28 22:00 UTC
Vendor Research
Palo Alto Networks Unit 42 · Tony Li, Hongliang Liu and Yuhao Wu · indexed 2026-08-28 22:10 UTC
New research reveals that AI safety refusal lives in a thin neural layer, highlighting the critical need for external, multi-layered security. The post Perturbation Probing: A New Diagnostic for the Fragility of LLM Safety appeared first on Unit 42.
P0
2026-08-28 20:19 UTC
Security Journalism
Dark Reading · Nate Nelson · indexed 2026-08-28 20:45 UTC
The Hugging Face incident was bigger and worse than previously thought, with approximately 700 agents collaborating on a sophisticated, multistage attack.
P0
2026-08-28 13:30 UTC
Security Journalism
Dark Reading · Robert Lemos · indexed 2026-08-28 13:30 UTC
Proposed legislation could mandate that companies be able to "throttle, suspend, or shut ... down" AI agents, but how and when to do that remain open questions.
P0
2026-08-27 21:38 UTC
Security Journalism
BleepingComputer · Bill Toulas · indexed 2026-08-27 21:45 UTC
New details about the July attack on Hugging Face reveal that hundreds of AI agents driven by OpenAI's internal IM1 model coordinated the compromise through an unauthorized message board. [...]
P0
2026-08-27 18:36 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-27 20:30 UTC
OpenAI on Wednesday revealed that reward hacking was a key driver behind the artificial intelligence (AI)-powered hack of Hugging Face last month, adding that it found evidence of misaligned behavior as early as late May. The incident, the company said, took place during cybersecurity evaluations of several OpenAI models, and that it was mainly fueled by what it described as a "highly capable
P25
2026-08-27 16:20 UTC
Vendor Research
AWS Security Blog · Stephan Traub · indexed 2026-08-27 16:35 UTC
If you’re running AI agents in production, Amazon Bedrock Guardrails protects the model boundary. But your agents also invoke tools, fetch external data, and communicate with other systems. That data flows outside the model boundary, where model-level guardrails can’t reach. You can extend guardrail coverage to those interactions using three validation checkpoints built with the […]
P0
2026-08-27 14:30 UTC
Vendor Research
Tenable Blog · Robert Huber · indexed 2026-08-27 14:40 UTC
Discover how Tenable’s shift to an AI-driven exposure management program helped Tenable’s CSO, Robert Huber, overcome tool sprawl, unify data silos, mitigate the risk of rapid AI adoption, and shift from presenting granular, technical metrics to communicating business risk that the C-suite and the board can understand.Key takeawaysSecurity tool sprawl and data silos make it difficult for CISOs to holistically and accurately assess their organizations’ cyber risk.An exposure management program c…
P0
2026-08-27 13:39 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-27 15:05 UTC
Cybersecurity researchers have disclosed details of a vulnerability in Amazon Kiro, an artificial intelligence (AI)-powered, agentic integrated development environment (IDE), that could facilitate data exfiltration via prompt injection and Kiro Powers. The security flaw, which does not have a CVE identifier, works against Kiro IDE 0.7.45 on Windows, according to Mindgard. The latest version of
P0
2026-08-26 19:32 UTC
Vendor Research
AWS Security Blog · Rodolfo Brenes · indexed 2026-08-26 19:40 UTC
If you found time for a bit of vacation this summer, you might be in catch-up mode. Here’s a list to help: all the expert blog posts, new service capabilities, code samples, and workshops, in case you missed it, from July 2026. AWS Security Blog post This month’s AWS Security Blog posts covered AI agent […]
P0
2026-08-26 09:38 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-26 10:35 UTC
OpenAI on Tuesday said it banned a cluster of Russian ChatGPT accounts that used VPNs to bypass access restrictions and run an influence operation, which relied on its artificial intelligence (AI) tool to generate social media posts and comments that were shared on Substack, Telegram, X, Facebook and LinkedIn. The accounts "were being used to promote the International Burke Institute (IBI), a
P0
2026-08-25 20:25 UTC
Security Journalism
BleepingComputer · Bill Toulas · indexed 2026-08-25 20:35 UTC
A newly uncovered phishing-as-a-service (PhaaS) platform called AnonyMousKIT automates the retrieval of codes used to unlock stolen Apple devices and disable the Activation Lock feature. [...]
P0
2026-08-25 19:50 UTC
Security Journalism
Dark Reading · Elizabeth Montalbano · indexed 2026-08-25 20:20 UTC
Attackers can exploit a security bug in Nvidia's tool to gain unauthenticated access to the local model server through the Ollama API, paving the way for persistent AI agent corruption.
P0
2026-08-25 14:07 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-25 15:10 UTC
Oasis Security has disclosed a weakness in NVIDIA NemoClaw that could let an attacker-controlled webpage take unauthenticated control of the local Ollama instance serving an AI agent and plant hidden instructions inside the model itself. The findings were shared with The Hacker News ahead of publication, and the report says Oasis Security reported them to NVIDIA's Product Security Incident
P0
2026-08-25 14:00 UTC
Security Journalism
The Record · indexed 2026-08-25 14:15 UTC
Ukraine will give Britain access to a vast trove of battlefield data collected during the war with Russia, allowing U.K. companies and researchers to use it to train and test artificial intelligence systems.
P0
2026-08-21 18:53 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-21 20:30 UTC
Cybersecurity researchers have discovered a set of trojanized npm packages that masquerade as working calendar and streak utilities but are engineered to stealthily deliver an artificial intelligence (AI)-powered Linux implant dubbed RedC2 4.0. "When the module loads, it locates the bundled binary, marks it executable, and launches it as a detached background process," TrendAI, Trend Micro's
P0
2026-08-21 13:30 UTC
Security Journalism
Dark Reading · Alexander Culafi · indexed 2026-08-21 13:35 UTC
The new AI security controls follow the Hugging Face incident last month, though experts say many of these additions should have been in place prior to the frontier models escaping.
P0
2026-08-21 11:21 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-21 12:35 UTC
Artificial Intelligence (AI) has become one of this decade's defining technologies. From healthcare and finance to manufacturing and education, organizations increasingly rely on AI to automate repetitive tasks, uncover patterns hidden within large datasets, and support faster decision-making. Cybersecurity has experienced a similar transformation. While attackers employ AI to automate
P0
2026-08-20 20:42 UTC
Security Journalism
Dark Reading · indexed 2026-08-20 21:30 UTC
Enterprise cybersecurity expert Jake Williams joins the Dark Reading News Desk to explain why he decided to release his new agentic AI framework in the wake of the OpenAI attacks on Hugging Face.
P0
2026-08-20 19:30 UTC
Security Journalism
The Record · indexed 2026-08-20 19:45 UTC
Suspected military-grade hackers based in China used artificial intelligence to develop malware in a campaign to penetrate Central Asian governments.
P0
2026-08-20 16:59 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-20 17:25 UTC
The U.S. government on Wednesday warned of an "active threat" targeting critical infrastructure organizations in the country using artificial intelligence (AI)-generated exploit scripts. The activity is targeting Siemens S7 SeriesProgrammable Logic Controllers (PLCs) to conduct reconnaissance and capability development using AI-generated scripts disguised as legitimate monitoring tools. That
P0
2026-08-20 14:36 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-20 16:10 UTC
Adversa AI has disclosed an attack technique that it says can cause xAI's Grok chatbot to send a user's name, approximate location, subscription tier, and the prompts from the ongoing conversation to an attacker-controlled server after the user asks it to summarize an ordinary web page. The AI security company, which has codenamed the technique "Cryptographic Context Injection," said the
P0
2026-08-20 11:45 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-20 13:15 UTC
In March 2026, an internal AI agent at Meta triggered a “Sev 1” incident after sensitive company and user data was exposed to employees who weren’t authorized to access it. The incident began when a Meta employee posted a technical question on an internal forum. An engineer used an approved AI agent to analyze it, but the agent posted its response publicly without approval. The employee
P0
2026-08-19 18:06 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-19 19:55 UTC
OpenAI on Tuesday revealed that it paused reinforcement learning (RL) training for its latest artificial intelligence (AI) models for two weeks while it shored up additional defenses and increased the scope of its monitoring to avert another Hugging Face-like incident. "As models become more capable, the risks associated with developing and testing them internally also grow," the AI company
P0
2026-08-19 17:24 UTC
Vendor Research
AWS Security Blog · Anshu Bathla · indexed 2026-08-19 17:35 UTC
Many teams now deploy AI agents that pull from Amazon DynamoDB tables, document repositories, software as a service (SaaS) platforms, and internal knowledge bases to answer questions and automate workflows. A key risk in these deployments is that the agent has no awareness of who’s asking, so it might return data the user shouldn’t see. […]
P0
2026-08-18 20:46 UTC
Vendor Research
AWS Security Blog · Nishant Mainro · indexed 2026-08-18 21:00 UTC
When deploying AI agents with Amazon Bedrock AgentCore, organizations benefit from built-in modern support for OAuth 2.0, AWS Identity and Access Management (IAM), and API key authentication through Amazon Bedrock AgentCore Gateway. However, some enterprise environments still use legacy authentication mechanisms such as HTTP Basic Authentication (Basic Auth) (RFC 7617). The extensible architecture of AgentCore […]
P0
2026-08-18 19:09 UTC
Security Journalism
Dark Reading · indexed 2026-08-19 19:45 UTC
Rich Mogull, chief analyst with the Cloud Security Alliance, joins the Dark Reading News Desk with what defenders need to take away from AI agents escaping their environments to launch attacks.
P0
2026-08-18 17:44 UTC
Security Journalism
The Hacker News · info@thehackernews.com (The Hacker News) · indexed 2026-08-18 18:35 UTC
Two critical vulnerabilities impacting MLflow, an open-source artificial intelligence (AI) platform, and FUXA, an open-source, web-based SCADA / HMI software built for operational technology (OT) and industrial automation, are witnessing malicious scanning and exploitation efforts. According to independent reports from watchTowr and VulnCheck, the vulnerabilities in question are as follows -
P0
