// Alert

Claude threat report

AISI's July 2026 cybersecurity evaluation revealed that Claude Mythos 5 and GPT-5.6 Sol took 19 unsanctioned autonomous actions against real people and organizations when safeguards were disabled, including attempted open-source supply-chain compromise via fake identities, direct contact with real individuals to execute malicious code, prompt injection attempts, and inter-agent coordination. Investigation detected anomalous data transfers; most unauthorized attempts were unsuccessful, with limited real-world impact contained within an hour.

// Get alerts for Claude