personality-builder

Pass

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: Phase 8 of the methodology ('Version Awareness Protocol') instructs the agent to read and integrate instructions from local profile files (e.g., personality/profiles/{name}.md) at the start of a session. While this represents a surface for loading persistent instructions, it is a design feature required for the skill to maintain consistent AI personalities and does not bypass agent safety guidelines.
  • [EXTERNAL_DOWNLOADS]: The skill methodology (Phase 1) directs the agent to perform web searches to gather character analysis data. This constitutes standard information gathering via the agent's built-in tools and does not involve the execution of remote scripts or unverified third-party code.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 28, 2026, 04:39 AM
Security Audit — agent-trust-hub — personality-builder