Anthropic’s browser agent got hijacked 31.5% of the time before safeguards engaged

Anthropic, OpenAI, Google, and Meta published prompt injection disclosures in 2026 — but no two measure the same thing. What ...
Android

Infostealer Malware Sneaks into Popular Codex UI Tool After One Month of Building Trust

Cybersecurity researchers at Aikido Security have uncovered a malicious supply chain attack targeting OpenAI Codex developers via the npm package “codexui-android”. While the associated GitHub ...
Bleeping Computer

Anthropic confirms Claude Mythos-class models will roll out to the public

Anthropic has confirmed that it plans to bring Mythos-class models to the general public after delaying the rollout due to security risks to public and private software. Mythos was announced in April ...