persona-auditor

Pass

Audited by Gen Agent Trust Hub on Jul 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill acts as a structural container that composes multiple specialized identities into an auditor role. It contains no executable logic or workflow scripts.
  • [SAFE]: No network operations, external downloads, or remote code execution patterns were detected in the skill definition.
  • [SAFE]: The skill does not access sensitive files, environment variables, or hardcoded credentials.
  • [SAFE]: The priming instructions define a specific evaluation persona ('Adopt an auditor's stance') and do not attempt to bypass safety guidelines or perform prompt injection attacks.
  • [SAFE]: All references in the 'composes' field point to internal system personas, which is standard behavior for persona-based agent architectures.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 11, 2026, 07:12 AM
Security Audit — agent-trust-hub — persona-auditor