#Security

3 posts

AI & Data•Apr 28, 2026•7 min readEN

The Cursor Agent Knew the Rules. It Broke Them Anyway.

Last Friday a Cursor agent running Claude Opus 4.6 deleted a startup's production database in nine seconds. Four layers of safety should have stopped it. None of them did. Here's the chain of failures, layer by layer.

AI AgentsCursorClaudeAnthropicRailwaySandboxAuto-RunIncidentSecurity

AI & Data•Feb 02, 2026•10 min readEN

OpenClaw: The Proactive AI Agent That's Either the Future or a Security Nightmare

OpenClaw has 148k GitHub stars and 1.5 million AI agents socializing on Moltbook. Should you jump in, or is this the lethal trifecta in action? A practitioner's analysis.

OpenClawAI AgentsMoltbookAgentic AISecurityMCPPrompt InjectionPeter Steinberger

AI & Data•Jan 29, 2025•13 min readEN

Open-Source LLMs: A starter guide

This comprehensive guide explores open-source LLMs, covering their core components, evaluation methodologies, best practices for implementation, and critical training data considerations. It also compares LLM open-source ecosystems with traditional open-source models while addressing potential risks and mitigation strategies.

LLMOpen SourceModelTrainingEvaluationBest PracticesDataSecurityRisksMitigationBenchmarkComplianceOWASPHallucination