Agentic Security Benchmark
Explore score history ↗Measures detection and prevention of agentic-AI security products on 286 attack and 875 benign samples across five AMTSO attack vectors via a scoring adapter harness.
- Released
- 2026-09-07
- Evaluates
- Language & Knowledge, Software & AI Compute, cs.AI
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
Agentic Security Benchmark code
No reported scores are on record for this benchmark yet.