external-cannbot-model-model-infer-graph-mode

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate technical guidance for optimizing machine learning models on Ascend NPUs using standard industry practices and official vendor libraries like torch_npu and torchair.- [SAFE]: External links point to the official documentation of TorchAir on the GitCode platform, which is consistent with the skill's purpose and the Ascend hardware ecosystem.- [SAFE]: No suspicious patterns such as prompt injection, data exfiltration, credential exposure, or obfuscation were detected. The skill instructions focus entirely on model performance and graph mode adaptation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 02:39 AM
Security Audit — agent-trust-hub — external-cannbot-model-model-infer-graph-mode