ux-ui-map-page-by-page

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill employs a local Node.js script scripts/page_artifacts.mjs for scaffolding and validating UI mapping files. The script implements safe path handling by validating the 'page' slug against a strict alphanumeric regex, preventing path traversal attacks.- [PROMPT_INJECTION]: The skill processes external web content, which presents a surface for indirect prompt injection.
  • Ingestion points: Web content (DOM snapshots, HTML) is captured and stored in ux_ui_map/requests/{page}.json and ux_ui_map/pages/{page}.md.
  • Boundary markers: The skill uses structured JSON keys and Markdown headers to separate data, though it lacks explicit instructions to ignore embedded commands within captured content.
  • Capability inventory: The skill possesses filesystem write access via its helper script and web navigation capabilities via Playwright (as indicated in the compatibility metadata).
  • Sanitization: The helper script validates the page slug via regex, but the captured DOM and HTML content are not sanitized before being written to the filesystem.- [DATA_EXFILTRATION]: No network activity or sensitive data access patterns were observed. All operations are confined to the repository's ux_ui_map/ directory.- [CREDENTIALS_UNSAFE]: No hardcoded credentials or access to sensitive configuration files (e.g., .env, .ssh) were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 03:54 AM