Skip to main content

long-context

Extend context windows of transformer models using RoPE, YaRN, ALiBi, and position interpolation techniques. Use when processing long documents (32k-128k+ token

95/100

Security score

The long-context skill was audited on Feb 28, 2026 and we found 5 security issues across 1 threat category. Review the findings below before installing.

Categories Tested

Security Issues

low line 522

External URL reference

SourceSKILL.md
522- **RoPE Paper**: https://arxiv.org/abs/2104.09864 (RoFormer)
low line 523

External URL reference

SourceSKILL.md
523- **YaRN Paper**: https://arxiv.org/abs/2309.00071
low line 524

External URL reference

SourceSKILL.md
524- **ALiBi Paper**: https://arxiv.org/abs/2108.12409 (Train Short, Test Long)
low line 525

External URL reference

SourceSKILL.md
525- **Position Interpolation**: https://arxiv.org/abs/2306.15595
low line 528

External URL reference

SourceSKILL.md
528- **Together AI Blog**: https://www.together.ai/blog/llama-2-7b-32k
Scanned on Feb 28, 2026
View Security Dashboard