role-persona
Pass
Audited by Gen Agent Trust Hub on Aug 11, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
role-personaCLI tool, which is a vendor-provided utility by 'dwsy', to manage roles, memory, and knowledge bases. This is the primary function of the skill and is explicitly documented. - [SAFE]: All data management is performed locally within the user's home directory (~/.pi/). There is no evidence of hardcoded credentials or unauthorized network exfiltration.
- [SAFE]: The daemon management functionality is used for performance optimization (reducing cold start times) and is managed through explicit CLI commands or auto-started upon the first call, following standard background service patterns.
- [SAFE]: The skill ingests information from conversations and external documents to build agent prompts. While this creates a surface for indirect prompt injection, it is a documented core architectural feature for maintaining persistent agent state and does not utilize unsafe execution methods.
Audit Metadata