alterlab-timesfm
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill demonstrates a strong security posture with no identified threats.
- It implements a mandatory preflight system checker (
scripts/check_system.py) that verifies available RAM, VRAM, and disk space before the model is loaded or downloaded, protecting the user's environment from crashes or resource exhaustion. - Model weights are downloaded from the official Google Research repositories on Hugging Face, which is a verified and trusted service.
- Code execution is strictly limited to well-documented scripts for forecasting, data processing, and visualization using standard, established libraries (e.g., pandas, torch, matplotlib).
- The processing of external CSV data is handled as numeric input for mathematical models, presenting no path for prompt injection or command execution via untrusted data.
Audit Metadata