dispatch

Pass

Audited by Gen Agent Trust Hub on Aug 16, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill implements a set of commands to manage the dispatching logic, enabling users to enable, disable, and configure model tiers via interactive prompts.
  • [DATA_EXPOSURE_AND_EXFILTRATION]: Reads and writes configuration data to specific local paths (~/.pi/agent/dispatch/settings.json and project-level .pi/dispatch/settings.json) to persist routing preferences across sessions.
  • [DYNAMIC_EXECUTION]: Dynamically creates and configures subagents at runtime using the platform's subagent creation tools, specifying different system prompts and toolsets based on the task complexity tier.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 16, 2026, 11:18 PM
Security Audit — agent-trust-hub — dispatch