calibration-check

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill performs expected statistical analysis on user-supplied data files. All external dependencies (pandas, pyarrow, fastparquet) are well-known, standard packages for data science tasks. The scripts implement local calculations for metrics like Brier score, ECE, and Log-loss without external network calls or sensitive file access.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 06:29 PM
Security Audit — agent-trust-hub — calibration-check