Amazon researchers used Anthropic AI to find cybersecurity weaknesses
Amazon researchers used Anthropic AI to find cybersecurity weaknesses
Publish Date: 2026-06-13 13:38:00
Source Domain: www.washingtonexaminer.com
Anthropic said it has blocked public access to its flagship Fable 5 and Mythos 5 models, rolled out earlier this week, after the Commerce Department barred their use by foreign nationals and users outside the United States.
Katie Moussouris, chief executive of cybersecurity firm Luta Security, said the jailbreak research was conducted by Amazon researchers who used a series of prompts to persuade Anthropic’s model to disclose information about several security vulnerabilities, according to the Wall Street Journal. Moussouris said Anthropic shared a copy of the report with her. She argued the information revealed by the model would be more useful to cybersecurity professionals defending networks than to malicious actors seeking to exploit them.
“Who at the White House evaluated this and thought it was a threat?” Moussouris said. “It’s a complete overreaction because this is exactly the kind of prompting that defenders would do.”
Amazon did not confirm that it performed jailbreak testing on Anthropic’s AI models, but did acknowledge that the company regularly consults the government on cybersecurity issues.
“As a leading cloud provider that serves a large number of private and public sector customers, it’s not uncommon for governments to seek our counsel on potential security risks,” an Amazon spokesman told the Washington Examiner. “When they occur, we don’t share the details of these discussions.”
Commerce Secretary Howard Lutnick notified Anthropic CEO Dario Amodei on Friday that Fable 5 and Mythos 5 would be subject to export controls, according to an administration official. The restrictions prohibit access by customers outside the United States, along with foreign nationals within the country.
Anthropic said it believes the government’s decision was tied to a recently identified jailbreak technique, allowing users to bypass safety guardrails in the models. The company described the method as one that uncovered only a…
