plan-with-baz

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a robust planning workflow that emphasizes user consent and read-only operations. It uses external tools (Baz MCP) for search and exploration but restricts their usage through clear search budgets and tool routing rules. The 'upload' functionality for sharing plans is explicitly gated behind user permission, and the instructions specifically forbid implementation until the user has signed off on the generated plan. All external tool calls (mcp__baz__update_plan, mcp__baz__link_plan_to_pr) are identified as legitimate vendor-owned resources for the 'baz-scm' author.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 01:49 PM
Security Audit — agent-trust-hub — plan-with-baz