eval-rubric-designer

Pass

Audited by Gen Agent Trust Hub on Jun 29, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is composed entirely of natural language instructions for structuring evaluation criteria. It does not contain any executable scripts, shell commands, or binary files.- [SAFE]: No evidence of data exfiltration, credential harvesting, or unauthorized network access was found. The skill does not reference any external URLs or remote resources.- [SAFE]: The instructions do not attempt to bypass safety filters or override agent behavior in a malicious way. It defines a structured process for a legitimate task (evaluating AI output).- [SAFE]: No obfuscation techniques or hidden commands were detected in the text or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 29, 2026, 10:25 PM
Security Audit — agent-trust-hub — eval-rubric-designer