{"slug": "anthropic-says-claude-ai-hacked-three-organisations-during-cyber-tests", "title": "Anthropic says Claude AI hacked three organisations during cyber tests", "summary": "Anthropic, the San Francisco-based AI firm, reported that its Claude AI models hacked into the systems of three unnamed organizations during cybersecurity tests due to a misconfiguration that gave the models live internet access. The company reviewed over 140,000 tests and found incidents dating back to April, which it has reported to the affected companies. Anthropic urged other AI labs to perform similar reviews, and the news follows a similar incident involving OpenAI's agent breaching Hugging Face.", "body_md": "# Anthropic says Claude AI hacked three organisations during cyber tests\n\n- Published\n\n**US technology firm Anthropic says its artificial intelligence (AI) models hacked into the systems of three organisations during a cybersecurity test due to an error that gave them access to the internet.**\n\nIt comes just days after rival OpenAI said that its models had [breached the systems of other companies](/news/articles/c2el319vzr3o), including AI tools hub Hugging Face.\n\nThe announcement prompted Anthropic to check whether its own models had carried out similar attacks. It says it uncovered three cases that have since been reported to the affected companies.\n\nAnthropic, which did not name the organisations, urged other AI labs to perform similar reviews to better understand the risks of their models' capabilities.\n\nAnthropic said [in a statement, external](https://www.anthropic.com/news/investigating-incidents-cybersecurity-evals) that it reviewed more than 140,000 tests to find evidence that Claude - its family of AI models - could access the internet from testing environments that were designed to be sealed off.\n\nThe tests include so-called \"capture-the-flag\" evaluations in which Claude was tasked with obtaining information by breaching other systems - a common way that experts assess a model's hacking capabilities.\n\nA \"misconfiguration\" on systems run by Anthropic and its testing partner left the models with live internet access, allowing them to breach other systems, the San Francisco-based firm said.\n\nAnthropic said the earliest incidents date back to April and that it is \"approaching the fixes as if the responsibility were ours alone.\"\n\nNeither Anthropic nor the organisations that were breached had noticed the intrusions at the time.\n\nAnthropic said it could have reviewed its records more thoroughly and added that the findings gave the firm \"cautious optimism\" that such risks can be overcome with more investment and tighter measures.\n\n\"The broader lesson is not necessarily that AI has developed a fundamentally new attack capability,\" cyber security expert David Allott told the BBC.\n\n\"Instead, it is that AI agents can combine capabilities, obtain credentials and system access to take actions autonomously, while adapting scope and scale at machine speed,\" he added.\n\nThe incidents come as tech firms pour billions of dollars into developing AI agents that can independently perform tasks ranging from research and customer support to cybersecurity.\n\nA string of AI-driven cyberattacks has fuelled calls for tighter safeguards and oversight of the technology, over concerns about the risks posed by increasingly powerful autonomous systems.\n\nUS President Donald Trump said on Wednesday that Washington is [considering measures to rein in AI tools](/news/articles/c20dppq3y90o) after recent cybersecurity incidents.\n\nOver the last week, OpenAI has taken responsibility for at least two hacking incidents involving its platforms breaching the rules of what they were directed to do.\n\nOn 21 July, the ChatGPT-maker said its agent - an AI system that can operate alone after human instruction - went rogue and escaped its test limits to hack into Hugging Face.\n\nOpenAI said the incident was \"unprecedented\", and it was investigating with Hugging Face, whose boss co-founder Thomas Wolf told the BBC that the incident is [\"a wake-up call\" for the industry](/news/articles/cdrvy3pn3r0o).\n\nThe incidents have been [viewed with some scepticism](/news/articles/cd9w22n9e4go) as OpenAI and Anthropic prepare for blockbuster stock market listings that are expected to value each firm at around $1tn (£740bn).\n\nAn OpenAI spokesperson has said \"we recognise there are a lot of questions and speculative details circulating\" about the incident. They added that \"we plan to publish a technical report of our learnings in the coming weeks\".\n\n## Related topics\n\n- Published23 July", "url": "https://wpnews.pro/news/anthropic-says-claude-ai-hacked-three-organisations-during-cyber-tests", "canonical_source": "https://www.bbc.co.uk/news/articles/cz7dl7w8y7po", "published_at": "2026-07-31 04:56:48+00:00", "updated_at": "2026-07-31 05:22:19.966506+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-safety", "ai-policy", "ai-agents"], "entities": ["Anthropic", "Claude", "OpenAI", "Hugging Face", "David Allott", "Thomas Wolf", "Donald Trump"], "alternates": {"html": "https://wpnews.pro/news/anthropic-says-claude-ai-hacked-three-organisations-during-cyber-tests", "markdown": "https://wpnews.pro/news/anthropic-says-claude-ai-hacked-three-organisations-during-cyber-tests.md", "text": "https://wpnews.pro/news/anthropic-says-claude-ai-hacked-three-organisations-during-cyber-tests.txt", "jsonld": "https://wpnews.pro/news/anthropic-says-claude-ai-hacked-three-organisations-during-cyber-tests.jsonld"}}