Technology ❯ Artificial Intelligence ❯ Cybersecurity

Vulnerabilities

Zero-Day Exploits AI Models Prompt Injection Attacks Data Exfiltration Prompt Injection Automated Attacks Patching Open-source Code AI Tools Software Security

Tests Validate Claude Mythos’ Autonomous Hacking Power as Banks and Regulators Escalate Reviews

Access is restricted under a private defensive program, giving defenders time to patch.

Stories older than 24h

Regulators Press Banks to Test Anthropic’s Mythos as Access Stays Locked Down

Powell and Bessent Warn Bank CEOs About Cyber Risks From Anthropic’s Mythos AI

Anthropic Unveils Claude Mythos Preview With Partner-Only Access Under Project Glasswing

Researchers Detail Prompt-Injection Attack That Bypassed Apple Intelligence Safeguards

OpenAI Says Prompt Injection Is a Lasting Threat to AI Browsers, Rolls Out RL Red‑Teaming for Atlas

Anthropic Study Shows AI Agents Can Autonomously Execute Lucrative Smart-Contract Exploits

Taiwan’s NSB Flags Security Breaches, Pro-China Bias in Five China-Made AI Models

Anthropic Says New Claude Sonnet 4.5 Can Code Autonomously for 30 Hours

Brave Says Perplexity’s Comet Still Vulnerable to Prompt Injection After Patch