skills/ghaida/design-skills/journey/Gen Agent Trust Hub

journey

Pass

Audited by Gen Agent Trust Hub on Jul 10, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's primary function is to provide design methodology, task analysis, and journey mapping. No malicious patterns were detected across any threat categories.
  • [DYNAMIC_EXECUTION]: The skill generates visualization diagrams using HTML and CSS. The instructions explicitly forbid the use of JavaScript, external fonts, or external CSS, which mitigates risks associated with cross-site scripting (XSS) or data exfiltration via remote resource loading.
  • [COMMAND_EXECUTION]: The skill utilizes Model Context Protocol (MCP) tools for integration with Figma and Pencil.dev. These are intended platform capabilities for design workflows and do not involve arbitrary shell command execution.
  • [PROMPT_INJECTION]: The skill contains no instructions designed to override agent safety filters or bypass system constraints. It uses natural instructional language to guide the agent in its design task.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 10, 2026, 03:54 PM
Security Audit — agent-trust-hub — journey