pm-image2pencil

Pass

Audited by Gen Agent Trust Hub on Jul 14, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill instructions and referenced templates focus exclusively on UI/UX design workflows. The logic follows a standard sequence of input gathering, tool initialization, and iterative design refinement.
  • [COMMAND_EXECUTION]: Interaction with the environment is restricted to the platform's 'pencil' MCP tools (get_editor_state, open_document, batch_design, get_screenshot, snapshot_layout). These tools are used appropriately to read and modify the design canvas.
  • [DATA_EXFILTRATION]: No network operations, external URL fetches, or sensitive local file access patterns were detected. Data handling is confined to the design document context.
  • [PROMPT_INJECTION]: No evidence of safety bypass markers, role-play instructions (DAN), or system prompt extraction attempts was found in the skill body or metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 14, 2026, 02:38 AM
Security Audit — agent-trust-hub — pm-image2pencil