Skip to main content

model-pruning

Enables efficient model compression and faster inference for LLMs using advanced pruning techniques like Wanda and SparseGPT.

Install this skill

or
83/100

Security score

The model-pruning skill was audited on Feb 21, 2026 and we found 3 security issues across 2 threat categories, including 1 high-severity. Review the findings below before installing.

Categories Tested

Security Issues

high line 92

Eval function call - arbitrary code execution

SourceSKILL.md
92model.eval()
low line 489

External URL reference

SourceSKILL.md
489- **Wanda Paper (ICLR 2024)**: https://arxiv.org/abs/2306.11695
low line 491

External URL reference

SourceSKILL.md
491- **SparseGPT Paper**: https://arxiv.org/abs/2301.00774
Scanned on Feb 21, 2026
View Security Dashboard
Installation guide →