steering

Pass

Audited by Gen Agent Trust Hub on Jun 25, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a domain-specific workflow for representation engineering (steering vectors). It uses local or explicitly requested models and writes artifacts to user-specified directories. The internal logic is contained within the project's own modules (activation_steering). No malicious patterns, data exfiltration, or unauthorized command executions were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 25, 2026, 12:09 PM
Security Audit — agent-trust-hub — steering