fair-esm2
Pass
Audited by Gen Agent Trust Hub on Jul 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [SAFE]: No malicious patterns such as prompt injection, data exfiltration, or obfuscation were detected. The skill instructions focus on documented usage of the fair-esm package.
- [EXTERNAL_DOWNLOADS]: The skill mentions downloading pre-trained model weights from dl.fbaipublicfiles.com. This is the official and well-known hosting platform for Meta AI research models.
- [COMMAND_EXECUTION]: Provides examples for submitting batch compute jobs using a remote compute API. This functionality is intended for high-performance protein embedding tasks and follows standard orchestration patterns described in the skill documentation.
Audit Metadata