cmd-persona

Pass

Audited by Gen Agent Trust Hub on Apr 16, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is designed to modify the agent's behavioral persona using a set of local Markdown files. The instructions guide the agent to adopt specific identities, communication styles, and priorities based on a predefined mapping.
  • [SAFE]: All persona files (personas/*.md) were analyzed and contain benign instructions focused on professional roles (e.g., 'Senior Developer', 'Principal Architect', 'Executive'). There are no instructions to bypass safety guidelines or ignore ethical constraints.
  • [SAFE]: The skill does not perform any network operations, access sensitive system files, or execute shell commands.
  • [SAFE]: User input is used strictly for mapping against a static table of aliases, which prevents path traversal or arbitrary file access.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 16, 2026, 05:11 PM