research/
13 pages · Updated September 1, 2026
Pages
- MCP: Model Context Pitfalls in an Agentic World
- Malware Found in Trending Hugging Face Repository "Open-OSS/privacy-filter"
- Universal AI Bypass: How Policy Puppetry Leaks System Prompts and Safety Data
- LLM Security Guide: Preventing Prompt Injection and Jailbreaking
- LLM Fake Function Injection: How to Prevent System Prompt and Tool Leaks
- How the Lethal Trifecta Expose Agentic AI
- Security Lessons from Recent AI Agent Incidents
- Hugging Face AI Agent Attack: What the Artifacts Reveal
- Hidden Prompt Injections Can Hijack AI Code Assistants
- Evaluating Prompt Injection Datasets
- DeepSeek-R1 Architecture
- MCP Security Alert: Extracting AI System Prompts via Parameter Abuse
- The First AI-Powered Cyber Attack: Anthropic Threat Report