Technology ❯ Artificial Intelligence ❯ Cybersecurity ❯ Vulnerabilities

Prompt Injection

Researchers Detail Prompt-Injection Attack That Bypassed Apple Intelligence Safeguards

RSAC says Apple fixed the flaw in recent OS updates after a private disclosure.

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

OpenAI Patches 'ShadowLeak' Flaw That Let ChatGPT's Deep Research Exfiltrate Gmail Data