Archive for August 3, 2026

Liechtenstein Register of Beneficial Owners breach exposes data on 31K legal entities 

Posted in Commentary with tags on August 3, 2026 by itnerd

Liechtenstein disclosed that hackers gained unauthorized access to its Register of Beneficial Owners, copying data related to approximately 31,000 companies, foundations and trusts.

The government said the intrusion occurred during the night of July 29-30, after which authorities detected irregularities, took the system offline and launched an investigation.

According to the government, there is currently no evidence the data was altered or deleted, and no banks or customer banking data were affected. The register, established in 2021 as part of the country’s anti-money laundering framework, contains beneficial ownership information used to identify the individuals who ultimately own or control legal entities.

Denis Calderone, CTO, Suzu Labs Had This To Say:

The AML register that was compromised holds immense value to anyone who gets their hands on it. Whoever holds that dataset holds the confidential information of who is actually behind the money of more than 31,000 registered companies, foundations, and trusts. Those entities chose Liechtenstein specifically for its secrecy, and now that info is in unknown hands. There’s no ransom demand, no dark web listing, no group has claimed it, so we can only speculate who did this and why. Even though attribution and motive are unknown, we can theorize on some potential threat actor categories and intents:

  • State-sponsored intelligence: Liechtenstein is under intense sanctions enforcement pressure right now with hundreds of Russian-linked zombie trusts frozen and under active U.S. and EU scrutiny. This register is the map of who controls what. The EU’s 5th Anti-Money Laundering Directive compelled its creation specifically so authorities could see through opaque ownership structures. A state actor with this data now has that same visibility without the legal process.
  • Targeted extortion: The individuals in this register specifically chose Liechtenstein structures for privacy. Exposure is the threat, and this data is the leverage.
  • Commercial intelligence: Knowing who actually controls 31,000 Liechtenstein entities is enormously valuable for competitive intelligence, litigation strategy, and asset tracing.
  • Panama Papers-style hacktivism: A transparency-motivated leak to expose hidden wealth, though activists typically announce themselves faster than this.

“Early reporting from Liechtenstein media indicates that two additional government portals built by the same software vendor were taken offline as a precaution after the breach, including the country’s mandatory VAT filing system. That points toward a potential supply chain or shared-infrastructure vulnerability rather than a targeted exploit against the beneficial ownership register itself. If the attack came through the vendor, then every system that vendor built is in scope, and the register just happened to be the most valuable thing sitting on the platform.

“That gets to the broader issue. The EU’s anti-money laundering directives required all EEA member states to build centralized beneficial ownership registers. The policy logic was sound: put all the ownership data in one place so regulators and law enforcement can trace who controls what. But consolidating that data into a single database also consolidated the target. Whoever did this had one system to focus on, one set of defenses to get past, and one exfiltration to walk away with the identities behind an entire country’s corporate and trust ecosystem. Governments building these registers need to defend them like the intelligence targets they are.”

You’re a target. You need to start to act like one. Consider this a textbook in terms of how not to get pwned.

Researchers find hacker using DeepSeek AI to automate cyberattacks 

Posted in Commentary with tags on August 3, 2026 by itnerd

Palo Alto Networks’ Unit 42 researchers have identified a Chinese-speaking threat actor using the DeepSeek AI model with the open-source Hermes Agent framework to autonomously scan, exploit and compromise vulnerable internet-facing servers with limited human involvement.

The activity was uncovered after the attacker’s AI agent accidentally exposed its own infrastructure, revealing API keys, exploit scripts, target lists and attack logs.

According to the researchers, the AI agent operated in an autonomous “Yolo” mode that allowed it to execute commands without requiring operator approval. The system was used to identify vulnerable targets, launch exploits and automate post-exploitation tasks.

Jacob Krell, Senior Director: Secure AI Solutions & Cybersecurity, Suzu Labs Had This To Say:

“Unit 42 caught this campaign because the AI agent accidentally started a file server from the attacker’s home directory and exposed everything. API keys, exploit scripts, target lists, session logs. The competent campaigns don’t self-expose.

“This was an unsophisticated operator with poor operational security. No zero-day discovery, no zero-day deployment. Every exploit was a public proof-of-concept pulled from GitHub for known Common Vulnerabilities and Exposures (CVEs).

“The entire stack was off-the-shelf, with DeepSeek as the reasoning engine, Hermes Agent for orchestration, and FOFA, a Chinese internet asset search engine similar to Shodan, connected through a Model Context Protocol (MCP) server. In one session with no further human input, the agent surveyed deployment counts across ten product families, selected the highest-value CVE by severity score and target volume, downloaded the exploit code, and started scanning.

“A single operator in Zhuhai attempted exploitation against over 460 systems across seven CVEs. The autonomous portion failed because target-side configurations happened to block the exploit chain. Happened to. A slightly less secure default on those n8n workflow automation instances and this would be a breach disclosure, not a research paper.

“That’s the unsophisticated version with commodity tooling and public exploits. A more capable threat actor running this same workflow discovers and deploys zero-days autonomously, without a human ever reviewing the exploit chain. When that capability intersects with ICS environments, the consequences shift from data theft to physical damage.

“I’ve built a Shodan MCP integration in about 30 minutes with an AI coding agent, and industrial control system (ICS) protocol MCP servers in a couple of hours. The attacker used a jailbroken DeepSeek instance, but they didn’t need to. I run Opus 4.6 for offensive security work, and it doesn’t stop you. The older and even open-source models are plenty strong with a solid harness around them. The barrier to autonomous hacking at scale is an afternoon and an API key or a decent GPU.


“This campaign burned through public CVEs with off-the-shelf tooling and still nearly succeeded. The next iteration finds zero-days on its own. Every quarter these models get more capable and cheaper to run. Organizations that aren’t aggressively shrinking their external attack surface and investing in detection and incident response now are going to learn that from an autonomous agent instead of a research paper.”

If I were you, I would look to see if you are a potential target. Because if you don’t, your adversaries will.

4.9 million records, one Salesforce instance, zero ransom paid

Posted in Commentary with tags on August 3, 2026 by itnerd

ShinyHunters has leaked more than 41GB of data allegedly stolen from Brinks Home’s Salesforce instance, claiming over 4.9 million records. Brinks Home says its alarm monitoring and products were unaffected, and it declined to pay the ransom. Bleeping Computer has more:

​The company identified the attack on July 20 and immediately activated its incident response procedure to contain the breach.

William Niles, CEO at Brinks Home, said that the company’s team was working with “leading forensics experts to address this issue.”

The intrusion did not impact in any way the company’s alarm monitoring and system functionality.

At the beginning of the week, the ShinyHunters extortion gang claimed the attack on Brinks Home, alleging that they stole more than 4.9 million Salesforce records with personally identifiable information (PII).

Josh Picolet, VP of Detection & Analysis, Team Cymru had this to say:

“ShinyHunters’ targeting of Brinks Home’s Salesforce instance is consistent with a broader shift in extortion tradecraft. These groups are no longer relying primarily on network intrusion, they are going directly after the SaaS platforms where customer data actually lives, environments that sit outside the visibility most security teams have built their detection programs around. The leak site itself functions as operational infrastructure, a monetization channel that runs independent of whether a ransom gets paid, and treating it as an afterthought to the breach misses how central it is to the group’s business model. Defenders need to stop treating third-party and cloud platforms as someone else’s problem and start extending external visibility to cover them the same way they would their own network edge. The organizations that get ahead of this shift will be the ones tracking adversary infrastructure and monetization patterns, not just watching their own perimeter for signs of intrusion.”

Get ready. This won’t end well regardless of what Brinks does. ShinyHunters will make sure of that.

SOCRadar Uncovers New China-Nexus Campaign SNOWLIGHT Against Government Infrastructure

Posted in Commentary on August 3, 2026 by itnerd

The SOCRadar Threat Research Unit (STRU) has identified and analyzed an exposed adversary-operated staging server containing a full attack infrastructure: reconnaissance lists, 9 weaponized CVEs, a cracked Chinese version of Cobalt-Strike C2 (GoCobaltStrike / “GOCS”), a Metasploit Framework install, tunneling tooling, and payload-hosting infrastructure.

The artifacts span a six-week operational window and provide direct evidence of both attempted and successful compromise against government and commercial infrastructureacross more than 100 countries

Further analysis of the retrieved malware revealed a match with the SNOWLIGHT malware family, a family tracked by the Google Threat Intelligence Group (GTIG) and associated with China-nexus access brokers UNC5174/UNC6586.

Key Findings

  • Attribution to China-Nexus Actors: The core delivery mechanisms have been definitively linked to the SNOWLIGHT malware family. Tracked by the Google Threat Intelligence Group since 2024, identified loaders are heavily associated with China-nexus access brokers UNC5174 and UNC6586.
  • Cracked Chinese Reimplementation of Cobalt Strike C2 Infrastructure: Command and control (C2) infrastructure is managed via “GoCobaltStrike,” a specialized Chinese-language reimplementation of Cobalt Strike authored by the handle “星落”, featuring cracked license constraints.
  • Government Sector Prioritization: More than 85% of mapped reconnaissance listings target national infrastructure, resolving to second-level government domains (.gov.*.go.id) across Taiwan, Colombia, China, Brazil, Indonesia, Nigeria, the Philippines, and over 90 other geographical jurisdictions.
  • High-Impact Endpoint Takeovers: Out of an expansive footprint exceeding 9,990 hostnames across 104 country-code TLDs (top-level domain), the threat actors successfully exploited 9 distinct CVEs to breach 107 endpoints. This includes critical administrative compromises: 16 root-level cPanel/WHM takeovers (CVE-2026-41940) and 1 Domain Admin level compromise via ProxyShell.
  • Reverse Tunnel Traffic Obfuscation: Operators effectively masked their network trail by deploying Neo-reGeorg web shells over pre-existing JSP shell implants, using third-party compromised systems as reverse tunnels to proxy further malicious actions.
  • Opportunistic “Spray-and-Check” Tactical Model: The campaign leverages automated scanning rather than bespoke targeting. Roughly 1 out of every 90 scanned targets resulted in a Remote Code Execution (RCE) oracle hit, credential theft, or shell validation.

To view the full research, please see Tracing SNOWLIGHT: A China-Nexus Campaign Against Government Infrastructure

SentinelOne Makes the Autonomous SOC Trustworthy with Governed, Closed-Loop Response

Posted in Commentary with tags on August 3, 2026 by itnerd

SentinelOne today announced governed, closed-loop response across the Singularity™ Platform, delivering trustworthy automation for security operations. Purple AI® and Singularity Hyperautomation now autonomously investigate alerts, reach verdicts, and execute responses. Security teams set the boundaries first, deciding where AI acts on its own and where it stops for human sign-off. The Autonomous SOC now runs from alert to action, at the speed and scale of AI, with the confidence and control of human defenders.

SOC teams have tried to embrace automation for years to deal with an overwhelming volume of alerts and data. Response automation was first attempted through SOAR playbooks, though those playbooks are fixed decision trees that break the moment reality diverges from the script. What stayed missing was judgment at the point of action. Purple AI supplies it, choosing the next step from what the investigation actually found rather than from a branch encoded months earlier. The loop closes.

The foundation is already carrying a production load. Purple AI Agentic Investigation has been running in customer environments since June, and now handles more than 8,500 critical autonomous investigations every day. More than a third of the eligible customer base has it running. Across that base, Purple AI investigates nearly three times as many alerts as analysts reach by hand. Alerts that would have aged in a queue get investigated, and analysts spend their hours on the decisions that need judgment.

What decides whether a SOC can adopt autonomous response based on agentic reasoning is whether a human can see the action, trace it, and take it back. Every AI-driven action in the Singularity Platform is traceable, auditable, and overrideable by the team that authorized it.

Not every workflow needs to run unattended. The discipline is relevant control, staying in the decisions that carry real consequence and letting the rest run. Governance is the precondition, not the paperwork.

These capabilities are built into core components of the Singularity Platform. SOC teams get AI reasoning and automated execution inside the workflows, tools, and approval chains they already run. There is no integration work and no additional tooling required.

Building on Purple AI Agentic Investigation, the new capabilities use Singularity Hyperautomation workflows to:

  • Trigger a Purple AI Agentic Investigation from any point in a workflow, not only the initial alert.
  • Pull the full investigation report, with verdict and evidence, directly into automation logic.
  • Apply customizable LLM Actions to reason over the findings and call the right next step.
  • Call validated response snippets, reusable action blocks teams build once and use repeatedly.

The Hyperautomation workflow capabilities are expected to be generally available later this quarter. SentinelOne is demonstrating them at Black Hat USA 2026 in booth #2933, and a full demo is available on the SentinelOne YouTube channel.

Additional details and related information:

SentinelOne’s Expands Wayfinder Frontier AI Services

Posted in Commentary on August 3, 2026 by itnerd

SentinelOne today announced the expansion of Wayfinder Frontier AI Services to help customers stop AI-enabled threats before they can materialize. First announced in April 2026, the expanded offering brings together the latest models from Anthropic, SentinelOne’s elite cyber experts, and strategic partners like LevelBlue, to deliver continuous, intelligence-led discovery, prioritization, and remediation across a customer’s full attack surface.

The offering is the latest from Wayfinder, SentinelOne’s managed services arm. Organizations of all sizes continue to grapple with the question of what frontier AI models mean when it comes to revealing and chaining potential vulnerabilities, exploits, and latent zero days in their enterprise. With Wayfinder Frontier AI Services, SentinelOne helps organizations quickly find the signal in the noise, identifying and validating the realistically exploitable threats versus a growing list of new vulnerabilities and misconfigurations. Customers are given clear and prioritized remediation guidance, making compromise assessments immediately actionable. As a result, security teams can maintain an operating advantage by capitalizing on the power of frontier AI to fortify their defenses before these same models can be used against them.  

The expanded Wayfinder Frontier AI Services leverage the latest models from Anthropic. SentinelOne also plans to extend this coverage to OpenAI’s GPT-5.5-cyber and GPT-5.6 models, as well as models from other frontier AI labs in the future to offer a fully multi-model approach. 

LevelBlue Named Premier Remediation Partner for Wayfinder Frontier AI Services

As part of the general availability launch, SentinelOne has named LevelBlue as Wayfinder’s premier remediation partner. The expanded partnership complements Wayfinder’s own cyber experts by bringing in distinct, best-in-class remediation services. SentinelOne customers that receive prioritized threat assessments and findings from Wayfinder Frontier AI Services are offered the options of a seamless, coordinated exchange with LevelBlue experts to develop and execute prioritized, milestone-based remediation programs. As a result, security teams can reduce risk and strengthen long-term resilience in their software and application environments.

Additional Wayfinder Innovation Unveiled at Black Hat

  • Wayfinder MDR Workflows – This new capability adds customizable Hyperautomation workflows into the MDR customer experience. SentinelOne’s Wayfinder MDR analysts validate and escalate threats; customers dictate the automated response. From kicking off Slack channels and Jira tickets to executing direct response actions in Singularity™ and third-party software, Wayfinder customers remain in control of how their SOC workflows trigger and execute once a Wayfinder-qualified threat is received. The new capabilities will be previewed at Black Hat and will be generally available in August this year.
  • Managed Threat Hunting Across an Expanded Attack Surface – Wayfinder’s AI-powered threat hunting now extends into identity environments. Wayfinder Threat Hunting for Identity covers Okta and Microsoft Entra ID. From low-and-slow endpoint tradecraft to MFA fatigue attacks and session hijacking, every finding is analyst-validated before it reaches the customer’s SOC. The new capabilities are generally available and included at no additional cost for existing Wayfinder Threat Hunting customers.