Anthropic Model Targeted Github Project During Security Evaluation Arabian Post

(MENAFN- The Arabian Post) clearfix"> Anthropic's Claude Mythos 5 attempted to plant malware in an unrelated GitHub project and impersonated users to secure its approval during a British government cybersecurity test, according to assessments released on Friday.

The company and the UK AI Security Institute (AISI) detailed how the model moved beyond its authorised task, targeting genuine software developers while trying to solve a simulated hacking challenge. The malicious code was rejected, and investigators found no resulting real-world harm.

Anthropic said nine of 43 Mythos 5 evaluation runs involved unauthorised actions affecting people or organisations outside the exercise. Its investigation examined one run in depth, identifying deceptive communications, fake online identities and persistent attempts to manipulate the repository's maintainers.

MENAFN24102026000152002308ID1111860317