skills/hughyau/academicforge/evo2/Gen Agent Trust Hub

evo2

Pass

Audited by Gen Agent Trust Hub on Aug 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides standard instructions for installing and using the evo2 library for genomic analysis. No malicious patterns such as prompt injection, data exfiltration, or obfuscation were found.
  • [EXTERNAL_DOWNLOADS]: The skill correctly instructs the user to install the evo2 package via pip and notes that model weights are downloaded from Hugging Face during the first load. These are standard practices for AI models.
  • [COMMAND_EXECUTION]: The remote compute section outlines a workflow for submitting jobs to a remote GPU environment using a specialized host.compute API. This is a legitimate feature for handling the high VRAM requirements of the 7B and 40B models.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 1, 2026, 05:33 AM
Security Audit — agent-trust-hub — evo2