amd-rocm

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a documentation repository for GPU computing on AMD hardware. No malicious intent or patterns were identified.
  • [SAFE]: External downloads (such as the amdgpu-install package from repo.radeon.com) and framework installations (PyTorch from pytorch.org) are sourced from official and trusted vendors.
  • [SAFE]: System-level operations, including the use of 'sudo' for package management and GPU resets, are consistent with the skill's stated purpose of environment setup and hardware administration.
  • [SAFE]: No evidence of prompt injection, data exfiltration, obfuscation, or unauthorized persistence mechanisms was found across the 98 analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 12:19 AM
Security Audit — agent-trust-hub — amd-rocm