Skills
skills/full-stack-skills/pencil-skills/pencil-mcp-get-editor-state/Gen Agent Trust Hub

pencil-mcp-get-editor-state

Pass

Audited by Gen Agent Trust Hub on Jun 23, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill is purely informational, designed to invoke an MCP tool (get_editor_state) to gather context about a design canvas.
  • [SAFE]: No prompt injection or behavior override patterns were detected. The use of 'CRITICAL' in the instructions is used for safety reinforcement regarding user intent.
  • [SAFE]: No external network requests, file system modifications, or credential harvesting patterns were found.
  • [SAFE]: No obfuscation, dynamic code execution, or persistence mechanisms are present.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 23, 2026, 04:05 PM
Security Audit — agent-trust-hub — pencil-mcp-get-editor-state