MalSkillBench

What is MalSkillBench?

MalSkillBench is a runtime-verified benchmark of malicious agent skills, with 3,944 malicious skills labeled along a taxonomy, measuring detection tool…

Released

2026-06-05

Evaluates

Agents, Language & Knowledge, Logistics & Operations

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.07131

MalSkillBench paper

• Paper https://arxiv.org/abs/2606.07131

Which sources cite MalSkillBench?

• MalSkillBench

Related Agents, Language & Knowledge, Logistics & Operations benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActiveSciBench
• AdaMem-Bench