ux-journey-architect
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were identified in the skill content or its associated scripts.
- [COMMAND_EXECUTION]: The skill facilitates the execution of legitimate shell commands to run Playwright tests (e.g., npx playwright test) and a Python utility (journey-export.py) for data transformation. These operations are standard for the skill's stated purpose of usability auditing and reporting.
- [EXTERNAL_DOWNLOADS]: The skill recommends well-known Node.js testing packages (@playwright/test, @axe-core/playwright) and includes a browser-side reference to the Chart.js library via a trusted CDN (jsdelivr) in its HTML templates. These are recognized industry-standard resources.
- [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection by ingesting untrusted user data such as journey maps and web application content. Evidence: (1) Ingestion points: journey-export.py (JSON files) and Playwright tests (web content); (2) Boundary markers: Absent; (3) Capability inventory: Subprocess execution (npx, python) and network access (WebSearch); (4) Sanitization: Minimal. This surface is inherent to its function as a UX auditing tool and no malicious instructions were identified.
Audit Metadata