profiling-analysis-profiling-computing

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill performs local data analysis on Ascend NPU profiling files. No network operations, credential exposures, or malicious code patterns were identified.
  • [COMMAND_EXECUTION]: The script scripts/op_perf_pivot_table.py uses subprocess.run to coordinate the execution of internal analysis scripts. This is a standard and safe implementation for modular script execution, using list-based arguments without a shell context.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:17 AM
Security Audit — agent-trust-hub — profiling-analysis-profiling-computing