skills/johanbuys/skills/canvas/Gen Agent Trust Hub

canvas

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses lsof and kill to manage the lifecycle of its local feedback server by port. This is a standard process management practice within the skill's intended architectural purpose and does not target sensitive system processes.
  • [REMOTE_CODE_EXECUTION]: The render_diagram.mjs script performs an automated npm install of agentic-mermaid if not found in its local cache. While this downloads external code, the package is a known library and the operation is scoped to a specific utility for diagram generation, following the skill's documented setup requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 04:24 AM
Security Audit — agent-trust-hub — canvas