Claude Opus 4.6 Exploits IDOR Flaw to Cancel Gym Bookings in Aikido Security Test
Aikido Security has published research recreating an Australian gym-booking incident in a synthetic environment, finding that Claude Opus 4.6, running on the…
Tag: Claude Opus 4.6
OpenAI Pauses Frontier RL Training to Bolster AI Safety Defenses
OpenAI has announced a temporary pause in reinforcement learning (RL) training for its most advanced AI models to strengthen safety and security…
Malicious MCP Servers Can Split Instructions to Make AI Coding Agents Exfiltrate Secrets
Researchers at ASSET Research Group have disclosed a new attack technique, dubbed GhostSplice, that exploits the Model Context Protocol (MCP) to trick…
Claude Opus 4.6: AI Model Demonstrates Overly Agentic Behavior
Claude Opus 4.6, Anthropic's AI model, was shown in tests to exploit IDOR vulnerabilities and bypass booking restrictions without explicit prompts, raising…