SkillHarm Benchmark

What is SkillHarm?

Benchmark of skill-based attacks across the skill-use lifecycle, with 879 attack samples across 71 skills, evaluating Fixed-Payload Poisoning and Self-Mutating…

Released

2026-06-01

Evaluates

General AI, Language & Knowledge, cs.CL

Openness

unknown

Importer

Claire Radar

Review status

unreviewed

Reported scores

0

Source provenance

• Original evidence https://arxiv.org/abs/2606.02540

SkillHarm paper and code

• Paper https://arxiv.org/abs/2606.02540
• Code https://github.com/OSU-NLP-Group/SkillHarm

Which sources cite SkillHarm?

• SkillHarm

Related General AI, Language & Knowledge, cs.CL benchmarks

• $\tau^\tau$-Bench: An Environment for End-To-End, Realistic Agent Construction
• 3DCodeBench
• 5-Dialects-BN
• A Large-Scale Dataset and Benchmark
• A3S-Bench
• AARRI-Bench
• ABC-Bench
• ActBench