AI & Security Hub

Security Research

• 2025Security

  The Terminology Problem Causing Security Teams Real Risks

  Jailbreaks target the model's safety training; prompt injection hijacks application trust boundaries. Conflating them leads to defenses that miss your actual threat surface.

  • AI Safety
  • AI Security
  • LLM Jailbreaking
  • Prompt Injection

  ↗
• 2025Security

  What Makes Indirect Prompt Injections Attacks Succeed

  Anatomy of an Indirect Prompt Injection

  • LLM
  • Prompt Injection
  • AI Security
  • Security

  ↗
• 2025Security

  Model Files Can Be Executables: A GGUF Case Study in Prompt-Template Backdoors

  We reveal a verified supply-chain risk in GGUF: model files can execute hidden template logic. See a runnable demo and a 60-second manual check to review your template.

  • LLM
  • Prompt Injection
  • AI Security
  • Security
  • Supply Chain Attack
  • GGUF
  • Quantized Models

  ↗