slime-rl-training
Pass
Audited by Gen Agent Trust Hub on Jun 29, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides documentation for a legitimate machine learning framework (slime) developed by a recognized research group (THUDM).
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to download the framework from its official GitHub repository and pull the latest Docker image. These are standard procedures for using this software.
- [COMMAND_EXECUTION]: The skill provides shell commands for environment setup and training execution. All commands are relevant to the primary purpose of RL post-training and do not show signs of malicious intent or unauthorized access.
Audit Metadata