timesfm-forecasting

Pass

Audited by Gen Agent Trust Hub on Mar 6, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches model weights from Hugging Face repositories (e.g., google/timesfm-2.5-200m-pytorch). These downloads originate from a well-known service and a trusted research organization.
  • [EXTERNAL_DOWNLOADS]: Interactive HTML visualizations generated by the skill reference the Chart.js library from a public CDN (cdn.jsdelivr.net).
  • [SAFE]: No malicious code, prompt injection, or unauthorized data access behaviors were detected. The skill implements safety-oriented preflight checks to prevent system resource exhaustion and correctly handles numerical data conversion by forcing float32 type casting, which mitigates risks of data-based injection.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 6, 2026, 10:32 AM