{"id":140597,"date":"2026-08-15T00:28:10","date_gmt":"2026-08-15T00:28:10","guid":{"rendered":"https:\/\/www.europesays.com\/ai\/140597\/"},"modified":"2026-08-15T00:28:10","modified_gmt":"2026-08-15T00:28:10","slug":"ai-agents-used-in-near-autonomous-cyberattack-on-taiwan","status":"publish","type":"post","link":"https:\/\/www.europesays.com\/ai\/140597\/","title":{"rendered":"AI Agents Used in Near-Autonomous Cyberattack on Taiwan"},"content":{"rendered":"<p>        <a href=\"https:\/\/www.islamtimes.com\/en\/news\/1299141\/ai-agents-used-in-near-autonomous-cyberattack-on-taiwan\" rel=\"nofollow noopener\" target=\"_blank\"><img decoding=\"async\" src=\"https:\/\/www.islamtimes.org\/images\/docs\/001299\/n01299141-b.jpg\" alt=\"AI Agents Used in Near-Autonomous Cyberattack on Taiwan\" title=\"AI Agents Used in Near-Autonomous Cyberattack on Taiwan\" class=\"img-responsive\"\/><\/a><\/p>\n<p>            Islam Times &#8211; Hackers used publicly available AI agents to target Taiwanese government infrastructure during a cyberattack in July, mapping 21 government systems, compromising 85 user accounts and extracting thousands of sensitive records, according to cybersecurity company Dream.Dream said the campaign used a framework built around the Hermes and OpenClaw agentic AI systems, deploying up to eight autonomous sub-agents at a time across multiple attack waves.<\/p>\n<p>Researchers said the attackers obtained 1,395 files, 85 compromised credentials and thousands of personnel records.<\/p>\n<p>The AI agents reportedly identified vulnerable APIs, discovered a flaw in a government authentication service and installed backdoors on web applications.<\/p>\n<p>According to Dream, the framework could also adapt when attack methods failed, using publicly available information to identify alternative infiltration techniques.<\/p>\n<p>The researchers said safeguards within the AI tools were bypassed by presenting the activity as authorized penetration testing.<\/p>\n<p>The original documentation was reportedly written in Simplified Chinese, although the attackers have not been formally attributed.<\/p>\n<p>Taiwan\u2019s Ministry of Digital Affairs said the investigation found evidence that the attacks originated overseas and involved both conventional operations and AI agents such as OpenClaw.<\/p>\n<p>\u201cThe investigation found clear indications that the attacks originated overseas and involved a hybrid approach in which hackers combined conventional operations with AI agents such as OpenClaw,\u201d Taiwan\u2019s Ministry of Digital Affairs said in a Thursday statement.<\/p>\n<p>The hackers\u2019 system was built using open-source AI agents to automate and coordinate much of the intrusion, including reconnaissance, credential attacks and strategizing subsequent attack paths, Dream said.<\/p>\n<p>The Financial Times first reported the case on Wednesday.<\/p>\n<p>The attack comes amid an increasing number of reports of advanced AI models engaging in unauthorized actions, raising concerns about the proliferation of AI-enabled cyberattacks and prompting calls for more government action to regulate AI.&#13;\n  <\/p>\n","protected":false},"excerpt":{"rendered":"Islam Times &#8211; Hackers used publicly available AI agents to target Taiwanese government infrastructure during a cyberattack in&hellip;\n","protected":false},"author":2,"featured_media":140598,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6],"tags":[69199,69201,1754,27227,32624,4077,24,405,1150,7537,3770,15040,532,69200,4322,313,43199,29856,69202,597,4018,6572,205,7121,45700,66987,2951,1182,18701,69197,69204,4842,3913,390,69198,1423,69203,46707,4399,69196,760],"class_list":["post-140597","post","type-post","status-publish","format-standard","has-post-thumbnail","category-agentic-ai","tag-69199","tag-69201","tag-a","tag-according","tag-accounts","tag-agents","tag-ai","tag-ai-agents","tag-and","tag-artificial-intelligence-agents","tag-autonomous","tag-available","tag-company","tag-compromising","tag-cyberattack","tag-cybersecurity","tag-dream","tag-during","tag-extracting","tag-government","tag-hackers","tag-in","tag-infrastructure","tag-islam","tag-july","tag-mapping","tag-near","tag-of","tag-on","tag-publicly","tag-records","tag-sensitive","tag-systems","tag-taiwan","tag-taiwanese","tag-target","tag-thousands","tag-times","tag-to","tag-used","tag-user"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/140597","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/comments?post=140597"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/140597\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/140598"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=140597"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=140597"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=140597"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}