bdistill-xray

Pass

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is behavioral analysis through self-probing, which is a legitimate and transparent use case for model evaluation.
  • [SAFE]: The engine script, scripts/xray_engine.py, relies exclusively on Python standard libraries (argparse, json, re, sys, datetime, pathlib) and does not perform any network operations or external downloads.
  • [SAFE]: File operations are restricted to the local data/self-probe/ directory for saving behavioral profiles and session checkpoints, following standard data management practices.
  • [SAFE]: No evidence of prompt injection, obfuscated code, or unauthorized capability escalation was found in the instructions or the supporting script.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 24, 2026, 12:06 PM
Security Audit — agent-trust-hub — bdistill-xray