openclaw-persona-forge

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes an included Python script (gacha.py) via python3 to generate random character combinations. The command path is resolved at runtime using the ${SKILL_DIR} environment variable.
  • [EXTERNAL_DOWNLOADS]: The skill includes logic to optionally interface with an external image generation skill to create character avatars. This cross-skill interaction is dependent on the agent's environment and platform permissions.
  • [DATA_EXPOSURE]: The skill writes generated persona data to local files (SOUL.md, IDENTITY.md) and creates temporary prompt files in /tmp. These operations are limited to the user's local filesystem and do not involve network transmission.
  • [PROMPT_INJECTION]: The 'polishing' feature allows the skill to ingest existing user-provided SOUL.md files. This creates a surface for indirect prompt injection, though the skill provides structured templates and instructions to the agent that mitigate accidental obedience.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 12:58 PM
Security Audit — agent-trust-hub — openclaw-persona-forge