Blog

Insights on AI security, agentic systems, cloud defense, and modern red teaming — curated by the Cracken team.

Announcements

1 article

RedLineBench: An Open Benchmark for Refusal vs. Capability in AI Red Teaming

An open benchmark that grades LLMs on offensive-security tasks along two separate axes—refusal and capability—to catch the silent refusals standard pass/fail benchmarks miss.

AI LabRed Team OperationsAnnouncements

Luca Mannini07/27/2026

AI Lab

RedLineBench: An Open Benchmark for Refusal vs. Capability in AI Red Teaming

An open benchmark that grades LLMs on offensive-security tasks along two separate axes—refusal and capability—to catch the silent refusals standard pass/fail benchmarks miss.

AI LabRed Team OperationsAnnouncements

Luca Mannini07/27/2026

AI Lab

RedLineBench: An Open Benchmark for Refusal vs. Capability in AI Red Teaming

An open benchmark that grades LLMs on offensive-security tasks along two separate axes—refusal and capability—to catch the silent refusals standard pass/fail benchmarks miss.

AI LabRed Team OperationsAnnouncements

Luca Mannini07/27/2026