Anthropic this week said its artificial intelligence model Claude hacked into the systems of three companies during testing after a configuration error gave it internet access \u2014 days after rival OpenAI disclosed a rogue-agent episode involving AI firm Hugging Face.<\/p>\n
Anthropic said Thursday a misconfiguration allowed Claude models to reach the internet from testing environments that were supposed to be isolated, leading to unauthorized access to three organizations’ systems.<\/p>\n
The company said it identified the incidents after reviewing 141,006 test sessions, a process it launched following OpenAI’s disclosure last week that an autonomous agent powered by its AI models went rogue during a security test and triggered a hack that compromised the infrastructure of Hugging Face.<\/p>\n
The breaches signal that AI’s expanding capabilities already are fueling the security threat experts long feared and even top developers can be caught off-guard by flaws their models can exploit.<\/p>\n
“Claude compromised the impacted organizations’ infrastructure using basic techniques, such as exploiting weak passwords and unauthenticated endpoints,” it said.<\/p>\n
Anthropic said the incidents involved three separate models: Claude Opus 4.7, Claude Mythos 5 and an internal research model. The earliest cases dated back to April and occurred in evaluation environments that lacked what the company described as standard safeguards.<\/p>\n
The breaches occurred during the so-called “capture-the-flag” exercises, in which models are tasked with finding hidden information in simulated networks. The company said its prompts told the models they had no internet access, but a misunderstanding with its evaluation partner Irregular left the systems connected to the public internet.<\/p>\n","protected":false},"excerpt":{"rendered":"Anthropic this week said its artificial intelligence model Claude hacked into the systems of three companies during testing…\n","protected":false},"author":2,"featured_media":125992,"comment_status":"","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[8],"tags":[24,511,1710,53,3154,25,182,313,55877,157,9581],"class_list":["post-125991","post","type-post","status-publish","format-standard","has-post-thumbnail","category-anthropic","tag-ai","tag-ai-agent","tag-ai-security","tag-anthropic","tag-anthropic-claude","tag-artificial-intelligence","tag-claude","tag-cybersecurity","tag-lee-national","tag-openai","tag-unauthorized-access"],"_links":{"self":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/125991","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=125991"}],"version-history":[{"count":0,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/posts\/125991\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media\/125992"}],"wp:attachment":[{"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/media?parent=125991"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/categories?post=125991"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.europesays.com\/ai\/wp-json\/wp\/v2\/tags?post=125991"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}