Technology ❯ Artificial Intelligence ❯ Cybersecurity

Vulnerabilities

Zero-Day Exploits Prompt Injection Attacks Prompt Injection Data Exfiltration Zero-Day Vulnerabilities AI Security Technologies AI Weights AI Browser Agents Software Security AI Bug Bounty Program Open-source Code Language Models Malicious Attacks Malicious Outputs Manipulation Jailbreaking Methods AI Models Patching

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

Industry guidance now favors layered defenses with limited agent privileges over expectations of a permanent cure.

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

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