add-sgl-kernel
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a static documentation/tutorial file. It contains no executable instructions for the agent beyond providing text and code templates to the user.
- [SAFE]: No network operations, credential harvesting, or data exfiltration patterns were detected in the provided code snippets.
- [SAFE]: The referenced dependencies (torch, triton, pytest) are standard industry-recognized packages for deep learning and testing.
- [SAFE]: All references to 'sgl-kernel' and 'sglang' are consistent with the skill's stated purpose and the author's identity ('sgl-project').
Audit Metadata