skills/jimliu/science-skills/evo2/Gen Agent Trust Hub

evo2

Pass

Audited by Gen Agent Trust Hub on Jul 2, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructs the user to install the evo2 package via pip, which is the official library for the described genomic model.
  • [SAFE]: Model weights are retrieved from Hugging Face (arcinstitute/evo2), which is a well-known and trusted repository for AI models.
  • [SAFE]: The remote compute section uses platform-specific abstractions (host.compute) to orchestrate GPU-intensive tasks. The patterns for script submission and artifact retrieval are consistent with standard HPC and cloud execution workflows.
  • [SAFE]: No obfuscation, data exfiltration, or unauthorized privilege escalation patterns were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 2, 2026, 01:21 AM
Security Audit — agent-trust-hub — evo2