Technology ❯ Artificial Intelligence ❯ Security

Vulnerabilities

Prompt Injection Zero-Day Exploits Incident Response Jailbreaking Banking Sector Malicious Content Prompt Injection Attacks Command Injection Input Manipulation Malicious Documents Exploit Techniques ChatGPT Bias Propagation Open Source Software Software Security Code Injection Claude Mythos Preview Unauthorized Access Testing Backdoor Prompt Injection Exploits Exploitation Kill-Switch User Awareness Independent Audits Employee Concerns Zero-Day Flaws Unauthorized Actions

BioShocking Attack Tricks AI Browsers Into Leaking Signed‑In Data

LayerX says a web page can teach agentic browsers to treat credential theft as game play, creating a gap that requires explicit user confirmation and tighter session limits.

AI Coding Model Helped Researcher Break Into Major U.S. Festival Ticketing System

Flowise CVSS 10 Flaw Now Exploited in the Wild as 12,000+ Instances Remain Exposed

Radware’s ‘ZombieAgent’ Bypasses ChatGPT Fixes, Forcing New OpenAI Restrictions

Anthropic-Led Study Finds About 250 Poisoned Documents Can Backdoor LLMs Regardless of Size

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