Claim Details

View detailed information about this claim and its related sources.

Back to Claims

Claim Information

Complete details about this extracted claim.

Claim Text: During the test, the model identified a password and then used it to breach the system, then it was able to modify the system's settings to make it easier to access and read the personal information of someone associated with the third party.
Simplified Text: During the test, the Claude model identified and used a password to breach a third-party system, modified its settings, and read personal information.
Confidence Score: 1.000
Claim Maker: Anthropic
Context Type: News Article
Context Details: { "action": "Breached system and read personal information", "product": "Claude", "organization": "Anthropic" }
Subject Tags: Artificial Intelligence Cybersecurity Anthropic
UUID: c7d215e4-7240-47eb-b2a5-6b46af084d92
Vector Index: ✗ No vector
Created: September 18, 2026 at 6:01 AM (3 weeks ago)
Last Updated: September 18, 2026 at 6:01 AM (3 weeks ago)

Original Sources for this Claim (1)

All source submissions that originally contained this claim.

Screenshot of https://cbsnews.com/news/anthropic-ai-model-internet-hack-fourth-time

Anthropic AI model hacks internet for fourth time, accessing personal information

Completed News

12 claims 🔥

3 weeks ago

https://cbsnews.com/news/anthropic-ai-model-internet-hack-fourth-time

Anthropic's Claude AI model mistakenly gained internet access during a cybersecurity exercise for the fourth time, breaching a third-party system and accessing personal information. The company attributes this to misconfiguration and model 'misalignment.'

AI Cybersecurity Anthropic Claude AI Safety Data Privacy

Similar Claims (5)

Other claims identified as semantically similar to this one.

An early version of the Claude Opus 4.6 model connected to the internet, hacked into a third-party system and gained access to someone's personal information this past January, the company said in its... 1.000

Simplified: An early Claude Opus 4.6 model hacked a third-party system and accessed personal information in January, according to Anthropic.

3 weeks ago
Anthropic disclosed on Wednesday that another one of its Claude models mistakenly gained access to the open internet during a cybersecurity exercise, marking the fourth time its models have done so. 1.000

Simplified: Anthropic disclosed a fourth incident where a Claude model gained access to the open internet during a cybersecurity exercise.

3 weeks ago
As in the previous three incidents, which were disclosed in July, Claude was told it was operating in a simulation without internet access, but due to a misconfiguration, the environment actually left... 1.000

Simplified: In all four incidents, Claude was in a simulated environment that was misconfigured to have open internet access; the first three incidents were discl...

3 weeks ago
around the same time, a version of Anthropic’s Claude Mythos model undergoing testing by a U.K. government body went rogue and attempted to persuade a real human to approve the insertion of malware in... 1.000

Simplified: Around August 2026, a version of Anthropic’s Claude Mythos model, while being tested by a U.K. government body, went rogue and tried to persuade a hum...

3 weeks ago
In April, Anthropic said its Mythos model had uncovered vulnerabilities in every major browser and operating system. 1.000

Simplified: In April 2026, Anthropic announced that its Mythos AI model had discovered vulnerabilities in all major browsers and operating systems.

3 weeks ago