openclaw-persona-forge

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes a bundled Python script (gacha.py) to generate randomized character combinations from a local dictionary. This is a controlled execution of its own code.
  • [SAFE]: Implements explicit sanitization logic for file naming, restricting character names to alphanumeric characters and hyphens before creating temporary files in /tmp for interoperability with other skills.
  • [SAFE]: The skill maintains a clear separation of concerns by acting as a text-based orchestration engine. It does not perform network operations itself, instead providing prompt text for external image generation tools or manual user use.
  • [SAFE]: File writing operations (SOUL.md and IDENTITY.md) are performed only upon user confirmation and at a user-specified directory, adhering to principles of transparency and user control.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:47 PM
Security Audit — agent-trust-hub — openclaw-persona-forge