library_name: transformers
pipeline_tag: text-classification
license: apache-2.0
base_model: AlexWortega/openjev
datasets:
- ProtectSkills/MaliciousSkillBench
tags:
- skillscreen
- agent-security
- nli
- msd
SkillScreen-2B-MSD
This model is described in the paper: SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models.
2B decision model for detecting malicious agent skills from SKILL.md. Trained on MaliciousSkillBench using Malicious-Structural-Disjoint (MSD), with an 8K input budget.
Based on OpenJev 2B. Full weights are at the root. The original LoRA adapter and classification head are in adapter/.
Use
Requires CUDA with BF16 support.
pip install huggingface_hub
hf download SkillScreen/SkillScreen-2B-MSD --revision v1.1 --local-dir skillscreen
pip install -r skillscreen/requirements.txt
python skillscreen/score.py path/to/SKILL.md
Native maliciousness score ≥ 0.5 is flagged as suspicious.
Checkpoint details · Export verification · Project page · Code
Jerrold Huang, Junwei Quan, Saiyue Lyu, Zihan Guo, Yingqiang Ge.
Citation
If you use SkillScreen's code, models, or predictions, or build models based on SkillScreen in your research, please cite our paper. If you release a derived model, please identify SkillScreen as its source and link to the original checkpoint.
@article{huang2026skillscreen,
title = {SkillScreen: High-Recall Screening of Malicious Agent Skills with Decision Models},
author = {Huang, Jerrold and Quan, Junwei and Lyu, Saiyue and Guo, Zihan and Ge, Yingqiang},
journal = {arXiv preprint arXiv:2610.17727},
year = {2026},
doi = {10.48550/arXiv.2610.17727},
url = {https://arxiv.org/abs/2610.17727}
}
Machine-readable citation metadata is provided in CITATION.cff. These citation requests do not add conditions to the licenses below.
License
Model weights (including the LoRA adapter and classification head), project-authored code, configuration, and code examples are licensed under Apache-2.0, for rights held by the SkillScreen contributors. The model card, documentation, citation metadata, and released provenance/evaluation reports are licensed under CC BY 4.0.
Research and commercial use, fine-tuning, and redistribution are permitted under these licenses without individual permission requests. Preserve the applicable attribution and license notices, and identify modifications as required by each license.
Upstream OpenJev and Qwen rights and notices remain applicable. See THIRD_PARTY_NOTICES.md, LICENSE-OPENJEV, and LICENSE-QWEN.
The v1.1 revision updates licensing and citation information. Its model weights, adapters, tokenizer, scoring code, and configurations are unchanged from v1.