skills/nvidia/skills/ad-graph-dump/Gen Agent Trust Hub

ad-graph-dump

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides technical instructions for configuring the AD_DUMP_GRAPHS_DIR environment variable to enable debugging output in TensorRT-LLM. All referenced paths and behaviors are consistent with the documented purpose of the tool.
  • [SAFE]: No obfuscation, data exfiltration patterns, or unauthorized remote code execution attempts were found. The example commands use standard local project scripts and temporary directories.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 06:14 AM
Security Audit — agent-trust-hub — ad-graph-dump