verl-rl-training
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely informational documentation for the verl library, providing legitimate training workflows and configurations.- [SAFE]: External references target official and well-known sources such as the verl GitHub repository (volcengine/verl) and the Hugging Face model hub (e.g., Qwen, OpenRLHF).- [SAFE]: Code snippets provided are standard Python and Shell commands for data preparation and model training within the verl framework.- [SAFE]: No evidence of prompt injection, data exfiltration, or malicious persistence mechanisms was detected.
Audit Metadata