🧰 Gemini 2.5 Pro

The items that name it 5

• Structured Security Explanations for Learning-Based Vulnerability Detection
  paperas tools2026-10-27

  LLM baseline for vulnerability judgment; VulnLens exceeds it by 2.2 points in F1 on PrimeVul, and by 16.6 points in accuracy and 7.8 points in F1 on SecVulEval.

• Is AI Coding Safe? Introducing the Agent Security League | Blog | Endor Labs
  articleas affected products2026-10-12
• Socket: New Study Identifies 53 Slopsquatting Targets Across 5 Frontier LLMs
  articleas affected products2026-07-23
• AI Security Briefing
  articleas affected products2026-07-18

  One of four LLMs successfully manipulated into making a fraudulent payment during Zscaler's test

• AI Security Briefing
  writeupas affected products2026-07-18

In every workspace you can read 9