IT News Analysis

1

AWS, Google, and Vercel Patch Agent Flaws That Let Tool Calls Skip the Model

Security flaws in agent infrastructure from Amazon Web Services (AWS), Google, and Vercel let untrusted or forged instructions reach an agent's tools with no check that a model turn had authorized them. In several of the attack paths, the model never ran at all, so system prompts, content filters, and model-level guardrails never got a chance to intervene. The affected products include Amazon Bedrock AgentCore's InvokeHarness API, Google's Agent Development Kit (ADK) for Python, and the Vercel AI SDK harness packages for the Codex and OpenCode coding agents. AWS has fixed the managed service, Google addressed the issues in ADK 2.5.0, and Vercel patched @ai-sdk/harness-codex in version 1.0.29 and @ai-sdk/harness-opencode in version 1.0.28. These are not identical vulnerabilities and do not share the same attack conditions. AWS involved an authenticated remote request, Google's paths required attacker-controlled session events or user-authored function calls, and V...

Aug 06, 2026

2

Chinese-Made Zbtlink Routers Ship With Backdoor That Opens Unauthenticated Root Shells

Cybersecurity researchers have disclosed details of a "factory-shipped backdoor" implanted in at least 20 Chinese router models from Zbtlink. According to a new report from VulnCheck, the implant appears in all 21 firmware images currently available from Zbtlink that span more than 2 years. The backdoors are designed such that they start automatically and attempt to beacon to Chinese command-and-control (C2) infrastructure as often as every 35 seconds. They masquerade as a Linux kernel thread, but are actually userland processes running with root privileges while blending their true functionality with other legitimate kworker processes. The "phone home" implants have been codenamed ENDLESSDOORS . "ENDLESSDOORS, at its core, is a small tool called rctl (remote control linux)," Jacob Baines, VulnCheck Chief Technology Officer, said. "Uploaded to GitHub on January 14, 2015 and never touched again, this obscure repository implements a simple co...

Aug 06, 2026

3

Ransom Cartel Creator Gets 16 Years in Prison for Operating Ransomware-as-a-Service

A federal judge in Alexandria, Virginia, sentenced Maksim Silnikau to 16 years in prison on August 5 for creating and running Ransom Cartel , the ransomware-as-a-service operation he stood up in 2021. Between 2021 and 2023, Ransom Cartel conspirators attacked at least 18 companies, including firms in California, New York and Nebraska, and others abroad, according to the Justice Department. Silnikau, a 40-year-old Belarusian national who worked under the handles "J.P. Morgan," "lansky" and "xxx," did not carry out most of those intrusions himself. He built the business around them: the locking software, the stolen credentials he bought from initial access brokers, and a hidden panel where affiliates monitored attacks, negotiated with victims and split proceeds. He ran a ratings system that rewarded the productive ones, and pushed ransom payments through cryptocurrency mixers. Sixteen years run past the 13 years and seven months handed to Yaroslav ...

Aug 06, 2026

4

AI Threat Readiness 101

Learn the four pillars of AI threat readiness and how security teams can reduce risk faster with detection, validation, and remediation built for today's threat landscape.

5

CISA Flags TeamCity CVE-2026-63077 RCE Flaw Under Active Exploitation in the Wild

A newly patched security flaw impacting on-premise versions of JetBrains TeamCity has come under active exploitation in the wild , according to the U.S. Cybersecurity and Infrastructure Security Agency (CISA). The vulnerability in question is CVE-2026-63077 (CVSS score: 9.8), a case of deserialization of untrusted data that could allow an unauthenticated attacker with access to a TeamCity server to bypass authentication checks and execute arbitrary operating system commands with the privileges of the TeamCity server process. "JetBrains TeamCity contains a deserialization of untrusted data vulnerability that could allow unauthenticated remote code execution via the agent polling protocol," CISA said . According to JetBrains, the vulnerability can be exploited by an unauthenticated attacker via the TeamCity agent polling protocol to sidestep authentication checks and execute arbitrary operating system commands. The exact impact varies depending on the privileges grant...

Aug 06, 2026

6

Snowflake Hacker Pleads Guilty Over Breaches Affecting at Least 100 Million People

Connor Riley Moucka pleaded guilty in Seattle federal court on Wednesday to computer fraud, wire fraud, aggravated identity theft and a related conspiracy over the 2024 breaches of Snowflake customer accounts . The intrusions reached at least 165 organizations and exposed records belonging to at least 100 million people. Moucka, 26, of Kitchener, Ontario, personally took at least $495,000 from ransoms and data sales. He is due to be sentenced on October 27 and faces a two-year mandatory minimum on the identity theft count and up to 30 years on the rest. What got the attackers in was old passwords. The credentials had been harvested years earlier by infostealer malware and never rotated, and the accounts had multi-factor authentication (MFA) switched off. No exploit, no flaw in the platform. The Justice Department has never named the company, in Wednesday's announcement or in the October 2024 indictment, identifying the victim only as a U.S. software-as-a-service (SaaS) pr...

Aug 06, 2026

7

The State of Shadow AI in 2026 (And How Attackers Are Taking Advantage)

AI adoption has exploded, but every new app, integration and extension introduces new threats and risks.

8

Over 250 ClickFix Domains Use Browser Fingerprinting to Hide macOS Malware Lures

A macOS ClickFix operation spanning more than 250 front-end domains now fingerprints visitors before deciding whether to show them a malware lure, a change Microsoft Threat Intelligence tracked on infrastructure it had been watching for weeks. The server-side gate hides the malicious page from crawlers and sandboxes while presenting selected Mac users with a fake software download. Microsoft said the wider cluster distributed MacSync and Atomic Stealer (AMOS) ; the chain it analyzed through the gate ended in AMOS. The attack still requires the user to copy and run an obfuscated command in Terminal. That command retrieves scripts and launches an infostealer targeting credentials, browser data, authentication stores, cryptocurrency wallets, and sensitive files. Microsoft has not disclosed victim numbers, targeted sectors, or the identity of the operators. Users should not follow any website, CAPTCHA, chat, or download instruction that asks them to paste text into Terminal. Micro...

Aug 05, 2026

9

OpenAI Disrupts Poipet Scam Network Using ChatGPT Across Multiple Fraud Schemes

OpenAI said it disrupted a Cambodia-based scam operation that used its generative artificial intelligence (AI) chatbot ChatGPT to facilitate a wide range of investment, romance, gambling, and law enforcement impersonation schemes. To that end, it banned a coordinated network of ChatGPT accounts likely originating from Southeast Asia and operating from the city of Poipet, a region with extensive ties to scam compounds and human trafficking in the past. The cluster of accounts is said to have used OpenAI's models to create and support the operation of fake online personas, generate and translate messages sent to scam targets, create promotional content for their fraudulent schemes, and assist with day-to-day activities. The promotional content included creating social media advertisements for "chatter" jobs in Poipet specifically targeting users in Bangladesh and India that promised a base salary of $800 (and a bonus of $100 for "full attendance"), alon...

Aug 05, 2026

10

Poison Claude Sells Discounted Claude Access While Its Operator Sees Every Customer Prompt

Cybersecurity researchers have discovered more than half-a-dozen services advertisements for illegal access to artificial intelligence (AI) models on underground cybercrime forums and messaging platforms. One such service, Poison Claude, claims to offer access to Anthropic's large language models (LLMs), including Opus 4.8, Opus 4.7, Opus 4.6, and Sonnet 4.6. "Advertisements for Poison Claude explain how the service can offer the cheap tokens: by taking advantage of free bonus credits, such as the US$100 bonus credit on AWS for Bedrock accounts," Okta researchers Jeremy Kirk and Mathew Woodyard said in an analysis published Tuesday. "The service plainly states on its website that: 'We add those accounts to our pool, your request is routed to a specific account under the hood (you don't see this), and you get charged 5-15% of the official per-token price depending on the model.'" Poison Claude accepts payments in cryptocurrencies. Once a cus...

Aug 05, 2026