Skills
skills/ascend-ai-coding/awesome-ascend-skills/mindspeed-llm-train-profiler/Gen Agent Trust Hub

mindspeed-llm-train-profiler

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes npu-smi info to check for hardware availability and source to initialize the CANN environment via set_env.sh.
  • [COMMAND_EXECUTION]: It generates a temporary shell script by copying the user's original script and appending profiling parameters, then executes it using torchrun.
  • [SAFE]: The skill explicitly prohibits modifying the user's original scripts, ensuring data integrity by working on timestamped copies.
  • [SAFE]: External references point to official Ascend NPU performance analysis tools on GitCode, a well-known platform for the target hardware ecosystem.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:16 AM
Security Audit — agent-trust-hub — mindspeed-llm-train-profiler