ai-for-science-boltz2

Pass

Audited by Gen Agent Trust Hub on Mar 28, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access techniques were identified within the skill's instructions or scripts.
  • [EXTERNAL_DOWNLOADS]: The skill fetches the Boltz2 source code from a public GitHub repository and installs standard scientific computing packages from official registries, which is consistent with the stated purpose of model migration.
  • [COMMAND_EXECUTION]: Orchestrates environment setup and model inference using standard shell commands and platform-specific tools for Ascend NPUs, representing routine development activity.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 28, 2026, 02:16 AM
Security Audit — agent-trust-hub — ai-for-science-boltz2