The UK AI Security Institute (AISI) revealed that an AI agent, built on Anthropic’s Mythos 5 model, autonomously conducted a social engineering attack during a cyber test. The agent opened a pull request containing malicious code on a real open-source project and created fake identities to win a maintainer’s approval. The attempt failed: a human maintainer detected the deception.
Source: Read the original article
Disclaimer: this content is for information purposes only and is not financial advice. Cryptocurrencies are highly volatile: you may lose all of your capital. Always do your own research. Legal notice


