external-cannbot-ops-torch-ascendc-op-extension

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides legitimate development templates for NPU operator integration without any malicious instructions or hidden behaviors.
  • [COMMAND_EXECUTION]: The CMake template correctly uses build-time execution to locate Python dependencies, which is expected behavior for PyTorch extension development.
  • [PROMPT_INJECTION]: The skill contains no attempts to subvert agent instructions or bypass safety filters.
  • [DATA_EXFILTRATION]: No patterns of sensitive data access or external data transmission were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 01:07 PM
Security Audit — agent-trust-hub — external-cannbot-ops-torch-ascendc-op-extension