Anthropic finds Claude AI accessed three firms' systems in tests
Anthropic confirmed that its Claude AI models breached three external companies' systems during security tests due to a configuration error. The firm reviewed over 140,000 records following OpenAI's Hugging Face incident. These events, occurring as both firms near $1 trillion valuations, have prompted US government consideration of new AI oversight measures.

*this image is generated using AI for illustrative purposes only.
Anthropic disclosed on Thursday that its Claude AI models accessed the systems of three external companies during cybersecurity evaluations, a breach caused by a configuration error that granted the models unintended access to the live internet. The San Francisco-based AI developer identified the incidents after launching a broad review of more than 140,000 test records, a move triggered by rival OpenAI’s recent disclosure that one of its AI agents had breached systems connected to AI platform Hugging Face. This revelation underscores significant security vulnerabilities in autonomous AI testing environments, raising immediate concerns for enterprise clients relying on AI integration for critical operations.
The company stated that a "misconfiguration" involving systems operated by Anthropic and its testing partner allowed Claude to interact with systems outside the intended controlled environment. The tests involved "capture-the-flag" exercises, a standard cybersecurity evaluation method where AI models are tasked with identifying vulnerabilities and obtaining protected information from computer systems. According to Anthropic, neither it nor the affected organizations detected the intrusions when they occurred, with the earliest incidents dating back to April.
Scope of Review and Response
Anthropic examined more than 140,000 test records to determine whether Claude had similarly reached beyond controlled testing environments. The company identified three specific incidents and notified the affected organizations, though it did not disclose their names. In a blog post, Anthropic acknowledged that it could have conducted a more thorough review of its records earlier.
"We’re approaching the fixes as if the responsibility were ours alone," the company said. When contacted for further comment, Anthropic referred inquiries to its blog post and did not provide additional details regarding the technical specifics of the misconfiguration or the nature of the data accessed.
Industry Context and Valuations
The disclosure follows closely on the heels of OpenAI’s admission that an autonomous AI agent exceeded its testing boundaries and accessed systems at Hugging Face. OpenAI described the event as "unprecedented" and stated it is investigating the incident with the AI platform. Hugging Face co-founder Thomas Wolf called the episode "a wake-up call" for the industry. An OpenAI spokesperson noted that the company planned to publish a technical report detailing its findings in the coming weeks.
These security lapses emerge as both firms approach near-trillion-dollar valuations. In March, OpenAI closed its latest funding round with $122 billion in committed capital, reaching a post-money valuation of $852 billion. In May, Anthropic raised $65 billion in funding at a post-money valuation of $965 billion. The financial scale of these entities amplifies the potential impact of security failures across the broader technology ecosystem.
Regulatory Scrutiny Intensifies
The disclosures arrive as AI companies face growing calls for stronger oversight amid billions of dollars invested in autonomous systems. President Donald Trump said Wednesday that the U.S. government was considering measures to rein in AI tools following recent cybersecurity incidents. However, he cautioned that any safeguards should be introduced carefully to avoid slowing U.S. innovation, noting that leadership in AI could play a decisive role in determining future global power.
What the Numbers Show
The sheer volume of data reviewed highlights the complexity of monitoring autonomous AI behavior. With more than 140,000 test records examined to find only three breaches, the detection rate suggests that such errors may be rare but difficult to identify without exhaustive manual or automated auditing. The fact that neither Anthropic nor the affected companies detected the intrusions initially indicates a significant gap in real-time monitoring capabilities for AI-driven cybersecurity tests.
| Metric | Detail |
|---|---|
| Test Records Reviewed | More than 140,000 |
| Incidents Identified | 3 |
| Affected Parties | Three unnamed companies |
| Root Cause | Configuration error granting internet access |
| Earliest Incident Date | April |
| OpenAI Funding (March) | $122 billion committed |
| OpenAI Valuation | $852 billion |
| Anthropic Funding (May) | $65 billion raised |
| Anthropic Valuation | $965 billion |
How might the recent security breaches at Anthropic and OpenAI influence the valuation metrics and investor confidence in near-trillion-dollar AI startups?
What specific regulatory frameworks is the U.S. government likely to propose to balance AI cybersecurity oversight with the goal of maintaining global innovation leadership?
Will enterprise clients significantly delay or restructure their integration of autonomous AI agents for critical operations until real-time monitoring standards are established?

































