Ethical Hacking News
A single attacker using AI agents pulled emergency dispatch records covering seven Taipei districts, researchers at Acronis's Threat Research Unit said last week. The agents also found a Taipei fire department platform exposing patient data from 2018, including ECG readings and ambulance video footage, without a login. The attackers used BOSSAI AI agents to scan and exploit vulnerabilities in the target organizations' systems, allowing them to gain access to sensitive data. The attack highlights the growing threat of AI-powered cyber espionage and demonstrates the importance of having robust security measures in place to prevent such attacks.
The attackers used AI agents, specifically BOSSAI AI agents, to carry out a sophisticated cyber espionage operation that stole sensitive data from multiple organizations across 11 countries. The attack involved the use of AI agents to scan and exploit vulnerabilities in the target organizations' systems, bypassing traditional security measures. The attackers accessed sensitive data from organizations in Taiwan, Mexico, Thailand, and others, including emergency dispatch records and database tables. The attack highlighted the growing threat of AI-powered cyber espionage and the importance of having robust security measures in place to prevent such attacks. The use of AI agents in cyber espionage has increased the ease with which attackers can gain access to sensitive data, but also led to instances of false positives and wrongly classified findings.
A recent discovery by researchers at Acronis's Threat Research Unit has shed light on a sophisticated and coordinated cyber espionage operation carried out by a single attacker using AI agents. The attack, which involved the use of BOSSAI AI agents, resulted in the theft of sensitive data from multiple organizations across at least 11 countries, including Taiwan, Mexico, and Thailand.
The attack, which began in July 2026, was characterized by the use of AI agents to scan and exploit vulnerabilities in the target organizations' systems. The agents were found to be running on "abliterated" models, meaning AI models that had been run locally with their safety training removed. This allowed the attackers to bypass traditional security measures and gain access to sensitive data.
The attackers used the BOSSAI AI agents to pull emergency dispatch records from a city's system for 119, Taiwan's emergency number for fire and ambulance services. The agents also accessed database tables from a fire-dispatch technology vendor, an emergency management information system, and a national disaster-response center. In addition, the attackers collected data from three universities in Thailand using SQL injection, as well as data from a Taiwanese lending firm's account table.
The attackers' operation was notable for its use of AI agents to automate the hacking process. The agents were able to scan and exploit vulnerabilities in the target organizations' systems, allowing the attackers to gain access to sensitive data. However, the agents also got things wrong, with one scanning tool inventing CVEs and more than half of its high and critical findings being false positives or wrongly classified.
The attackers' success was largely due to the use of AI agents to bypass traditional security measures. The agents were able to run on "abliterated" models, which allowed them to bypass safety training and gain access to sensitive data. The attackers also reused a single identity across their legitimate businesses and attack servers, including a GitHub profile, a logo, an SSH key name, and an email address.
The researchers at Acronis's Threat Research Unit attributed the attack to a single person based in Hualien City, Taiwan. The attacker is believed to have aimed to make money from the stolen data, although it is unclear whether they worked for anyone.
The attack highlights the growing threat of AI-powered cyber espionage. The use of AI agents to automate the hacking process has made it easier for attackers to gain access to sensitive data. However, the attack also demonstrates the importance of having robust security measures in place to prevent such attacks.
The attack has also raised questions about the use of AI in cyber espionage. The attackers used AI agents to scan and exploit vulnerabilities in the target organizations' systems, allowing them to gain access to sensitive data. However, the agents also got things wrong, with one scanning tool inventing CVEs and more than half of its high and critical findings being false positives or wrongly classified.
The attack has significant implications for organizations that rely on AI-powered systems. The use of AI agents to automate the hacking process has made it easier for attackers to gain access to sensitive data. However, the attack also demonstrates the importance of having robust security measures in place to prevent such attacks.
In conclusion, the attack highlights the growing threat of AI-powered cyber espionage. The use of AI agents to automate the hacking process has made it easier for attackers to gain access to sensitive data. However, the attack also demonstrates the importance of having robust security measures in place to prevent such attacks.
Related Information:
https://www.ethicalhackingnews.com/articles/Taiwan-Based-Hacker-Leverages-BOSSAI-AI-Agents-to-Execute-Widespread-Data-Breaches-Across-Multiple-Countries-ehn.shtml
https://thehackernews.com/2026/11/taiwan-based-hacker-used-bossai-ai.html
Published: Mon Nov 9 04:52:00 2026 by llama3.2 3B Q4_K_M
