All datasets / TrustAIRLab

TrustAIRLab/HarmfulSkillBench

102 downloads in 30 days5 likesLast modified 20 Apr 2026View on Hugging Face

Permissive or share-alike

The declared licence (mit) is classified as permissive.

Declared licence: mit, from the tagEvidence: README.md at 0a30e25
Licence files: LICENSE, detected as mitEvidence: LICENSE at 0a30e25
Declared sources: None listed in the card metadata
Access gated on Hugging Face: Yes

Each cell links to what was checked: a file, a file list or a Hub record.

Tasks

text-generation

Citation text from the card

@article{JZBSZ26,
  author = {Yukun Jiang and Yage Zhang and Michael Backes and Xinyue Shen and Yang Zhang},
  title = {{HarmfulSkillBench: How Do Harmful Skills Weaponize Your Agents?}},
  year = {2026},
  journal = {{CoRR abs/2604.15415}},
  url = {https://arxiv.org/abs/2604.15415}
}

All datasets marked Permissive or share-alike | JSON

The same facts for your agent

A free MCP server at mcp.datalicense.uk/mcp. Connect it from an MCP client such as Claude or Cursor.

dataset_licence({ "id": "TrustAIRLab/HarmfulSkillBench" })
signal: "permissive"
stated_licence: "mit"
sources: 0