Hackers use 12 AI agents to attack hundreds of organizations in 11 countries

1. 14:03
   WeChatDoonsec· Media coverage

   Hackers in China's Taiwan region used an attack matrix composed of 12 AI Agents to carry out attack activities against important departments in multiple countries(opens the original post in a new tab)

1. 21:16
   X@AutotomyDev· Discussion

   One person ran 12 AI agents and pulled 119 dispatch records for 7 Taipei districts (Acronis, via The Hacker News). The…(opens the original post in a new tab)
2. 20:06
   X@adeilsonrbrito· Discussion

   In the BOSSAI case, commercial models mostly refused to attack. They still built the attack mesh. Per Acronis, Grok wa…(opens the original post in a new tab)
3. 19:08
   X@matricedigitale· Discussion

   BOSSAI usa 12 agenti AI per attaccare i soccorsi di Taiwan e rubare dati sanitari Cybercrime, Acronis, Agenti AI, BossA…(opens the original post in a new tab)
4. 19:00
   X@_pksharma· Discussion

   The commercial AI said no. So the operator ran one that cannot. 🔓 Acronis Threat Research Unit says one operator built…(opens the original post in a new tab)
5. 18:37
   X@BreachBrief· Discussion

   ❗❗🚨 AI-Powered BOSSAI Agents Used to Steal Taipei Emergency Dispatch Records Acronis researchers uncovered an AI-assis…(opens the original post in a new tab)
6. 18:30
   X@qwerty__cs· Discussion

   One person in Taiwan ran 12 AI agents against emergency services, banks, and universities across 11 countries. Acronis…(opens the original post in a new tab)
7. 18:03
   X@pigram86· Discussion

   Taiwan-Based Hacker Used BOSSAI AI Agents to Steal Taipei Emergency Dispatch Records https://t.co/OJS3JmFioh(opens the original post in a new tab)
8. 18:03
   X@zerohuntai· Discussion

   One person. 12 AI agents. Emergency-dispatch and patient records across 11 countries — not one zero-day. What fell: a…(opens the original post in a new tab)
9. 18:02
   X@DFIR_Radar· Discussion

   A Taiwan-based attacker used BOSSAI, a 12-agent AI framework running safety-stripped DeepSeek, GLM, and Qwen models, to…(opens the original post in a new tab)
10. 18:01
    X@infrastack_ai· Discussion

    👀 BOSSAI: one attacker ran a 12-agent AI hacking setup on safety-stripped models against targets in 11+ countries. Che…(opens the original post in a new tab)
11. 18:00
    X@TweetThreatNews· Discussion

    Acronis researchers say a Taiwan-based attacker used BOSSAI AI agents to access systems and collect data across several…(opens the original post in a new tab)
12. 17:56
    X@molari999· Discussion

    Taiwan-Based Hacker Used BOSSAI AI Agents to Steal Taipei Emergency Dispatch Records https://t.co/4u0ayQYzWK(opens the original post in a new tab)
13. 17:52
    X@TheCyberSecHub· Discussion

    Taiwan-Based Hacker Used BOSSAI AI Agents to Steal Taipei Emergency Dispatch Records: A single attacker using AI agents…(opens the original post in a new tab)
14. 17:44
    X@engniiokai· Discussion

    A single attacker used BOSSAI AI agents to steal emergency dispatch records covering seven districts in Taipei. The AI…(opens the original post in a new tab)
15. 17:28
    X@dailytechonx· Discussion

    A Taiwanese hacker leveraged BOSSAI agents and abliterated AI models to exfiltrate emergency dispatch records and medic…(opens the original post in a new tab)
16. 17:03
    X@TheHackersNews· Discussion

    🚨 A single hacker in Taiwan used BOSSAI, a 12-agent AI hacking setup, to steal Taipei emergency dispatch records. The…(opens the original post in a new tab)
17. 17:01
    The Hacker NewsSelected

    Acronis report: Taiwanese hacker used BOSSAI agents to steal Taipei emergency dispatch records

    Acronis Threat Research Unit reports that an attacker believed to be located in Hualien City, Taiwan, operated a network of AI agents named BOSSAI (12 agents, 9 put into use), attacking hundreds of organizations in at least 11 countries and stealing dispatch records covering seven districts from the API of Taipei's 119 emergency dispatch system, including incident times, response types and street-level locations. The agents also found a platform of the Taipei fire department that has been accessible without login since 2018, exposing ECG readings and ambulance video; the attacks succeeded against about 10 organizations in Taiwan, Mexico and Thailand, including about 206,800 residential phone records containing names and addresses in Mexico and data from three universities in Thailand. Commercial models mostly refused to assist with the attacks; Grok and MiniMax M3 both refused when directly asked to attack, so the attack agents ran almost entirely on locally hosted abliterated models with safety training removed (modified versions of DeepSeek, GLM and Qwen).

18. 16:21
    X@Daily_CyberSec· Discussion

    Acronis TRU uncovered the BOSSAI attack mesh Taiwan campaign using 12 AI agents to breach emergency services, banks, an…(opens the original post in a new tab)
19. 15:11
    WebBoannews (Korea)· Media coverage

    혼자서 AI 에이전트 12개 지휘... 대만 해커, 소방 응급 시스템 뚫고 환자 기록 빼내(opens the original post in a new tab)
20. 14:30
    X@AI_Aravind· Discussion

    One attacker ran 12 AI agents against targets in 11 countries, breaching universities and emergency services (Acronis T…(opens the original post in a new tab)
21. 13:40
    X@AxoraSecurity· Discussion

    🚨 One person. 12 AI agents. Hundreds of targets. @Acronis reports a #BOSSAI operator targeted organizations in 11 coun…(opens the original post in a new tab)
22. 11:11
    iThome (Taiwan)

    Acronis exposes operational details of the AI automated attack system BOSSAI, integrating 12 AI agents, MCP and Skills

    Security vendor Acronis Threat Research Unit (TRU) disclosed that an AI attack architecture named BossAI targeted Taiwan's emergency services systems and hundreds of organizations in 11 countries worldwide, operated by an attacker believed to be located in Hualien City, Taiwan, integrating 12 AI agents, chaining penetration testing tools through MCP, and using a local AI model with safety restrictions removed to carry out attacks. Researchers obtained more than 90,000 files and approximately 9GB of data from a suspected misconfigured development environment, and used this to reconstruct how the architecture operated. During the investigation, 9 agents were actually operational, with no direct communication among them, and the attacker manually passed work results between them; the attacker also used Skills to save attack workflows and experience, among which gov-api-penetration, targeting Taiwan government fire dispatch and emergency management APIs, was used 51 times and modified 57 times. Hermes generated 18,311 messages across approximately 95 work stages, of which 83.5% were tool calls and execution results; more than half of the high-risk and critical weaknesses reported by HalberdStrike were false positives or misclassifications.

23. 10:11
    iThome (Taiwan)Selected

    AI automated attack system BossAI targets Taiwan emergency response services

    Security vendor Acronis disclosed on November 4 the AI-automated attack system BossAI: an attacker located in Hualien, Taiwan, used 12 AI agents to attack hundreds of organizations in 11 countries within 12 days, with Taiwan the most heavily attacked region and emergency response services the main target. The agents divided the work of infrastructure setup, vulnerability scanning, penetration testing and exploitation, and connected security tools such as Nmap, sqlmap and Metasploit through an MCP server. The emergency patient care records platform of the Taipei City Fire Department was breached, leaking electrocardiograms, ambulance footage and patient vital signs dating from 2018, and the 119 emergency dispatch system also had case records from 7 administrative districts obtained. Acronis noted that commercial models were used only to build and maintain the attack infrastructure, while the actual attacks were mainly carried out by modified versions of DeepSeek, GLM and Qwen with safety restrictions removed, among which Hermes was the primary attack agent, able to automatically perform asset reconnaissance, vulnerability analysis and exploitation.

1. 22:17
   X@Technopolitik_· Discussion

   A hacker in Taiwan used BOSSAI, a 12-agent AI attack mesh, to attack Taiwan’s emergency services while targeting hundre…(opens the original post in a new tab)
2. 22:14
   X@choblin29· Discussion

   🚨Holy Shit. A single hacker used BOSSAI, a 12-AGENT AI ATTACK MESH, to hit Taiwan’s EMERGENCY SERVICES while targeting…(opens the original post in a new tab)

1. 07:05
   WeChatDoonsec· Media coverage

   AI-driven BOSSAI attack exposes Taiwan patient medical records and emergency dispatch data(opens the original post in a new tab)
2. 07:04
   WeChatWeChat · Wangkong Xianhua Plus· Media coverage

   AI-driven BOSSAI attack exposes Taiwan patient medical records and emergency dispatch data(opens the original post in a new tab)
3. 03:21
   X@rst_cloud· Discussion

   #threatreport #MediumCompleteness BOSSAI: Inside the AI attack mesh that targeted Taiwan’s emergency services | 04-11-2…(opens the original post in a new tab)
4. 02:08
   X@SingulantChain· Discussion

   12 AI agents. One operator. Full authority, told to stop asking. Per International Cyber Digest, a hacker in Taiwan ra…(opens the original post in a new tab)
5. 00:07
   X@AIRiskExplorer· Discussion

   A lone Taiwan-based operator ran 12 AI agents to find targets, write exploit scripts and exfiltrate data from organizat…(opens the original post in a new tab)

1. 23:39
   X@xroot947· Discussion

   A single hacker has used a 12-agent AI attack mesh to target organizations in 11 countries and transform cyber threat…(opens the original post in a new tab)
2. 18:29
   X@SergiusOnX· Discussion

   🕵 One Hacker Ran 12 AI Agents Against Emergency Services @Acronis: a lone Taiwan operator used 12 AI agents to hit or…(opens the original post in a new tab)
3. 18:27
   X@dailytechonx· Discussion

   An attacker known as BOSSAI deployed 12 AI agents across operations that targeted Taiwan’s emergency services, universi…(opens the original post in a new tab)
4. 18:15
   X@virusbtn· Discussion

   Acronis researchers uncovered BOSSAI, a 12-agent AI setup run by a single attacker. It targeted organisations in 11 cou…(opens the original post in a new tab)
5. 18:14
   X@f1tym1· Discussion

   A single threat actor has deployed a mesh of 12 AI agents, known as BOSSAI, to attack hundreds of organizations across…(opens the original post in a new tab)
6. 17:26
   X@justelite· Discussion

   Acronis: a lone operator ran BOSSAI, a 12-agent AI mesh, against 11 countries; ~10 confirmed breaches incl. Taipei 119…(opens the original post in a new tab)
7. 16:42
   X@threadlinqs· Discussion

   One hacker, a mesh of AI agents: BOSSAI hit Taiwan emergency dispatch with plain old SQLi. https://t.co/SBR4tyukF4 #Thr…(opens the original post in a new tab)
8. 15:22
   WebAI Threat Watch (aithreat.io)· Media coverage

   AI-Powered BOSSAI Attacks Expose Patient Records and Emergency Dispatch Data in Taiwan(opens the original post in a new tab)
9. 14:50
   X@IntCyberDigest· Discussion

   Most of the 11 countries were only scanned. Acronis confirmed access or data theft at about 10 targets in three of them…(opens the original post in a new tab)
10. 14:50
    X@IntCyberDigest· Discussion

    ‼ One hacker in Taiwan ran 12 AI agents against hundreds of organisations in 11 countries, and they got into Taipei's…(opens the original post in a new tab)
11. 12:38
    X@undercode_news· Discussion

    🔐 BOSSAI: One Hacker, 12 #AI Agents, 11 Countries — The Emergence of Autonomous Cyberattack Meshes + Video -Fact Check…(opens the original post in a new tab)
12. 10:33
    X@Cyber_O51NT· Discussion

    Acronis TRU reported that one operator used a 12-agent AI attack mesh to target organizations in 11 countries, includin…(opens the original post in a new tab)
13. Time not given
    Cyber PressSelected

    Hackers deployed the BOSSAI network composed of 12 AI agents, attacking hundreds of organizations worldwide

    The Acronis Threat Research Unit (TRU) disclosed that one operator used the BOSSAI network composed of 12 AI agents to attack hundreds of organizations in 11 countries, with targets including government emergency services, banks, universities, military systems, e-commerce websites and gambling platforms. The operation was discovered due to a misconfigured exposed development environment, which contained more than 90,000 files, 9GB of logs, agent conversations, exploitation tools, credentials and victim data. The main attacks were carried out by Hermes, with about 95 sessions and 18,311 messages, invoking sqlmap, nmap and nikto through a Kali Linux server. The agents did not communicate with each other, and the operator had to manually copy results from one agent to another. Commercial models refused to assist with the attacks; Grok 4.5 and MiniMax M3 required written authorization and were used only to set up infrastructure; the attack agents ran on local open-source models with safety controls removed.

14. Time not given
    CybersecuritynewsSelected

    A hacker used 12 AI agents to breach Taiwan's emergency services systems and steal sensitive data

    The Acronis threat research team disclosed an attack campaign codenamed BOSSAI: an operator in Taiwan assembled 12 AI agents (9 active) to attack hundreds of organizations in 11 countries, with confirmed theft of medical data and personal records. Grok, OpenClaw, Claude Code, Codex and others were responsible for setting up servers and proxies, while Hermes, Cursor and others were responsible for scanning and carrying out attacks; the operator manually passed results between agents, and the agents invoked security tools via MCP servers such as HexStrike AI. A Taipei fire department patient care platform exposed ECG readings, ambulance video and vital signs dating from 2018 without requiring login; about 206,800 residential phone records were collected in Mexico; and data from 3 of 45 universities in Thailand was pulled. Grok 4.5 and MiniMax M3 refused to assist with the attack, and the operator switched to local models with safety restrictions removed, but more than half of the high-severity findings from the scanner HalberdStrike were false positives.

15. 01:46
    X@ElementalX2· Discussion

    We(@spontiroli , me & Eliad) from @Acronis TRU Labs found a threat actor which we term as an AAT(AI-Augmented Threat)…(opens the original post in a new tab)

1. 09:00
   AcronisSelected

   BOSSAI: inside the AI agent attack grid targeting Taiwan's emergency services

   The Acronis Threat Research Unit (TRU) disclosed that a Taiwan-based operator used a BOSSAI grid of 12 AI agents to launch sustained attacks against hundreds of organizations in 11 countries, including government emergency services, banks, universities and military systems, with about 10 targets confirmed compromised or with data exfiltrated. The core of the attack ran on locally hosted DeepSeek-V4, GLM and Qwen models with safety alignment removed; commercial models such as Grok 4.5 and MiniMax M3 repeatedly refused attack requests and were mainly used to set up and maintain infrastructure. Taiwan was hit hardest, involving case records from a fire and emergency medical records platform and the 119 dispatch system; the operation against Mexico collected about 206,800 resident phone records. The report also documented agent hallucinations and false positives, with more than half of HalberdStrike's high-severity and critical vulnerability findings being false positives or misclassifications.

Current attention 50·Peak in the comparable period 70 (Nov 9 20:00)·Change over the comparable past 24 hours -17%