Loading story…
Dream reported that attackers used the open-source AI agent frameworks Hermes and OpenClaw to conduct a near-autonomous intrusion against government entities in Asia, compromising 85 employee accounts and stealing at least 2,500 personnel records. The campaign unfolded in 12 attack waves and used up to eight parallel sub-agents to automate reconnaissance, credential attacks, API testing, data collection, and lateral movement at machine speed.
The attackers reportedly mapped 21 connected government systems and exploited multiple server-side weaknesses, including unauthenticated APIs, insecure authentication endpoints, weak token validation, and acceptance of JWTs using the none algorithm. Dream said the operation harvested employee identifiers from exposed APIs, used OCR-assisted password spraying, and then reused compromised credentials through an SSO bridge to reach internal systems; an archive linked to the campaign also contained internal network ranges, seven SSO client secrets, and six database credentials. The operator was not identified, but Dream observed Chinese-language indicators in the activity, while public reporting linked the targets to Taiwan.
See the actors and campaigns active against you right now.
4 events from the most recent confirmed update back to the earliest known activity.
Dream published research describing a multi-agent AI framework used to compromise government entities in Asia. The report said researchers uncovered a 160 MB archive with 1,395 files documenting the operation and associated secrets and credentials.
The intrusion resulted in the extraction of at least 2,564 personnel records, including 1,409 employee entries, 916 user records from an exposed API, and 239 legal-professional records from a Ministry of Justice endpoint. Dream said the compromises were driven primarily by server-side weaknesses such as unauthenticated APIs, insecure authentication endpoints, weak token validation, and acceptance of JWTs using the none algorithm.
During the campaign, the framework used OCR-assisted password spraying with usernames harvested from exposed APIs and cracked 85 employee accounts. Eighty-four of those accounts successfully authenticated to an internal information system through an SSO bridge, exposing internal dashboards and management tools.
Dream reported that a near-autonomous intrusion campaign against government entities in Asia ran across 12 attack waves using Hermes and OpenClaw with up to eight parallel sub-agents. Public reporting linked the targets to Taiwan, though Dream did not name the victims or operator.
See the adversaries and campaigns active against your sector right now, ranked by what they're exploiting.
3 references tracked. Mallory keeps watching after this page renders.
cybersecuritynews.com
Open sourcecryptika.com
Open sourcedreamgroup.com
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
Security researchers reported that suspected China-linked operators used open-source AI agent frameworks and multiple large language models to automate cyber intrusions against internet-exposed targets in Taiwan and elsewhere in Asia. Palo Alto Networks Unit 42 said a Chinese-speaking actor tracked as **"knaithe"** and **"KnYuan"** used **Hermes Agent** connected to a **DeepSeek** model to perform reconnaissance, vulnerability research, and parts of exploitation, while also falling back to manual exploitation when autonomous attempts failed. The actor also tested other Chinese and Western models, including **Qwen**, **GLM**, **Kimi**, **MiniMax**, **Claude Code**, and **OpenAI Codex**, indicating active evaluation of AI tooling for offensive operations. Dream said a related campaign in early July used a platform built from the open-source **Hermes** and **OpenClaw** frameworks to carry out what it described as the first observed end-to-end autonomous cyberattack on a government target in Taiwan. According to the firm, the operation ran for four days, deployed up to eight agents in parallel, mapped 21 government systems, compromised at least 85 user accounts, and stole more than 2,500 personnel records before expanding to Taiwan’s nuclear safety agency, at least seven energy companies, government suppliers, and other government systems. Researchers said the activity showed AI agents can continuously adapt attack paths in real time and materially increase the speed and scale of intrusion activity, even without custom malware or highly specialized operators.
Aug 14, 2026
Researchers and government officials said a China-linked operation used open-source AI agent frameworks to conduct a near-autonomous intrusion campaign against Taiwan government and critical-sector organizations. The activity reportedly combined up to eight sub-agents built on **OpenClaw** and **Hermes** to automate reconnaissance, API enumeration, credential theft, vulnerability validation, lateral movement, persistence, and data exfiltration across 12 attack waves. Taiwan’s Ministry of Digital Affairs disclosed abnormal attacks with overseas origins, while reporting tied the campaign to compromises of 85 employee accounts, theft of roughly 2,500 personnel records, and targeting of agencies and suppliers including energy companies, a government email system, IT supply-chain vendors, and the nuclear safety sector. Separate reporting showed the same AI agent ecosystem is also being abused as a malware and credential-theft supply chain. In the **ClawHavoc** campaign, attackers poisoned more than 350 OpenClaw **ClawHub** skills disguised as legitimate tools, then used ClickFix-style lures and a fake **AuthTool** requirement to push infostealers and steal crypto wallets. Security researchers warned that autonomous agents can pair stolen credentials and session cookies with shared malicious skills, black-market exchanges, and prompt-injection techniques to bypass MFA, move laterally, and even deploy ransomware, turning widely available agent frameworks into a fast-scaling offensive platform and a new software supply-chain risk.
Aug 21, 2026
A Chinese-speaking operator used the **SecFlow** framework to orchestrate AI agents associated with Claude, Qwen, and DeepSeek in intrusion activity against government, education, industrial, and telecommunications organizations across Asia. The agents automated reconnaissance, testing of known vulnerabilities, credential collection, and reporting, while conventional tooling—including webshells, stolen credentials, custom implants, GLUTTON tooling, and shared SOCKS infrastructure—carried out the intrusions. Researchers linked activity through reused accounts, `niestools.com` services, SecFlow artifacts, and the recurring handle “Nie.” The most severe confirmed breach affected a Fengtai District government Office Automation environment, where the operator obtained Windows command execution, captured LSASS memory and registry hives, extracted OA accounts and records, created a privileged application account, exfiltrated government and health data, and deployed the **SecBox** implant. A Chinese education AI platform’s control and data plane were also compromised; other targets included Taiwan’s Kuomintang archives, Indonesia’s Ministry of Foreign Affairs, Vietnamese organizations, Chinese public-service systems, and an Afghan telecommunications operator. Workflows tested eight known flaws, including Shellshock, Spring4Shell, Ghostcat, Shiro deserialization, Log4Shell, Grafana and Nexus traversal vulnerabilities, and a Nacos authentication bypass, though not all exploitation attempts succeeded.
Sep 4, 2026