pyvene-interventions

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill utilizes well-established open-source libraries (pyvene, torch, transformers) designed for machine learning research and model interpretability.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download of the pyvene library and pre-trained models from established registries.
  • pip install pyvene for library installation from PyPI.
  • AutoModelForCausalLM.from_pretrained for downloading model weights from HuggingFace.
  • pv.IntervenableModel.load for fetching intervention configurations from HuggingFace repositories.
  • [SAFE]: External links are directed to legitimate project documentation on GitHub and academic papers on arXiv and ACL Anthology.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 12:55 AM
Security Audit — agent-trust-hub — pyvene-interventions