rwkv-architecture

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE] (SAFE): No malicious patterns detected. The skill consists of documentation and standard Python/PyTorch code for implementing and using the RWKV model architecture.
  • [EXTERNAL_DOWNLOADS] (SAFE): Installation instructions point to standard Python package repositories and the official PyTorch index (pytorch.org). Dependencies are well-known open-source libraries including torch, transformers, rwkv, deepspeed, and wandb.
  • [COMMAND_EXECUTION] (SAFE): Code snippets include standard environment variable configuration for GPU acceleration (RWKV_CUDA_ON) and model path specifications. No suspicious shell commands or privilege escalation attempts were found.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:06 PM