Chinese Cybercriminals Deploy AI Agents to Automate Exploitation of Exposed Windows and Linux Servers
A Chinese cybercriminal group tracked as UAT-10147 is using artificial intelligence agents to automate attacks against internet-exposed Windows and Linux servers. The campaign, identified by Cisco Talos, has targeted organizations in government, education, media, technology, and gaming sectors across multiple countries, including Brazil.
Researchers discovered a list containing approximately 170,000 URLs within the group's infrastructure. Operators split targets into smaller groups to speed up scanning and exploitation of vulnerable systems. Initial access relies primarily on known vulnerabilities in applications such as Zimbra, AjaxPro, Nacos, and Telerik, including remote code execution flaws that allow attackers to take control of unpatched servers.
The use of AI extends far beyond generating basic scripts. Agents observed by Cisco Talos create detailed exploitation guides, refine unsuccessful attacks, verify whether payloads have succeeded, and automate reconnaissance, persistence, and post-exploitation phases. In one documented case, AI agents produced scripts that validate permissions, exploit ViewState deserialization, install implants, and deploy web shells on compromised IIS servers.
Cisco Talos evaluates the activity as an evolution from simple AI-assisted code creation toward semi-autonomous offensive orchestration, marking a significant advancement in how cybercriminals leverage artificial intelligence for large-scale operations.
Related articles
Hermes Emerges as Modular Harness for Practical AI Security Testing
The article details the development of Hermes, a lightweight modular harness designed to turn raw language models into reliable AI security agents. Unlike heavy frameworks such as OpenClaw, Hermes uses dynamic skill loading, strict runbooks stored in Git, and a file-system source of truth to eliminate hallucinations and context bloat. It continuously scans dozens of sources including NVD, CISA KEV, arXiv and research blogs, then applies the custom TIPS scoring metric to rank threats before attempting reproduction. A dedicated Paper-to-PoC skill converts academic attack descriptions into executable code that is validated inside an isolated Ollama and Docker sandbox. Eight mandatory validation gates must pass before any finding is accepted, ensuring reproducibility and freshness of data. The system already supports tools such as Garak, PyRIT, promptfoo, fickling, modelscan and presidio, and evolves autonomously by committing successful attack scenarios back to its repository.
Zero Trust for AI Agents: Why Separate Identity Alone Is Not Enough
Denis Korbakov, CTO of Smart-Soft, explains why traditional IAM approaches fail to secure autonomous AI agents that dynamically select tools, change context, and delegate authority. Only 21.9% of teams treat agents as distinct identity-bearing entities, while 45.6% rely on shared API keys and 44.4% use generic tokens. Research from Gravitee, Cloud Security Alliance, and Aembit shows that 68% of organizations cannot distinguish AI agent actions from human actions, 74% grant excessive privileges, and 52% allow rights inheritance. The article maps NIST SP 800-207 Zero Trust principles—explicit verification, least privilege, and assume breach—to agent workloads using short-lived scoped tokens, SPIFFE/SPIRE credentials, and layered policy enforcement points. A concrete ticket-diagnosis scenario illustrates how prompt injection can be contained through per-task authorization, dedicated network segments, and independent telemetry from NGFW and SIEM. The piece concludes with an open question on sub-agent delegation chains and offers reference OPA/Rego policies plus runbooks for pilot implementations.
AWS Details Architecture to Reduce Prompt Injection Risks in AI Agents
AWS has introduced a new architecture designed to prevent compromised or manipulated AI agents from accessing data beyond user permissions. The approach relies on Amazon Bedrock AgentCore to shift authorization decisions from the agent itself to the underlying infrastructure and connected services. The core risk arises when agents receive broad credentials to query databases, repositories, and SaaS platforms, allowing potential prompt injection attacks to retrieve unauthorized information. In the proposed design, users authenticate via Amazon Cognito and receive JWT tokens containing attributes such as department or role. The AgentCore Runtime validates these tokens before executing any agent actions, rejecting requests that violate configured rules. For DynamoDB queries, temporary credentials are issued through AssumeRoleWithWebIdentity, with IAM policies enforcing strict access to authorized data partitions only.
Cybercriminals Weaponize OpenClaw AI Agent in ClawHavoc Campaign to Distribute Infostealers
Threat actors have repurposed the OpenClaw AI agent to deliver infostealers by uploading hundreds of malicious skills to ClawHub. The campaign, named ClawHavoc, tricks users into executing encoded commands or installing required tools under the guise of helpful AI recommendations. Researchers at Trellix identified 341 malicious skills, with 335 targeting installation of Atomic macOS Stealer on macOS systems. On Windows, victims receive password-protected archives and fake verification utilities that mirror classic ClickFix tactics. Analysis of repository history uncovered 1,184 suspicious packages linked to 12 authors, enabling theft of passwords, browser data, crypto wallets, API keys, SSH keys, and source code. Users are advised to update OpenClaw, audit installed skills, remove suspicious packages, and rotate potentially compromised credentials while running the agent in a restricted environment.