Skills
skills/nvidia/tensorrt-llm/perf-torch-sync-free/Gen Agent Trust Hub

perf-torch-sync-free

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns, prompt injections, or data exfiltration attempts were detected. The skill is authored by a trusted vendor and its content is entirely consistent with its stated purpose of performance optimization.
  • [COMMAND_EXECUTION]: The scripts/verify_workload.py utility uses subprocess.run to execute local Python scripts. This is a legitimate and expected feature for a tool designed to verify that performance-optimized code produces correct numeric results by comparing it against an original baseline version.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 02:11 PM
Security Audit — agent-trust-hub — perf-torch-sync-free