liquid-themes

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the user to execute local scripts and CLI tools for validating theme code.
  • Evidence: node <plugin-root>/scripts/validate-shopify-schema-ids.mjs referenced in SKILL.md for schema validation.
  • Evidence: theme-check . referenced in SKILL.md for linting.
  • [EXTERNAL_DOWNLOADS]: The skill suggests downloading and installing a development tool from a well-known service.
  • Evidence: npm install -g @shopify/theme-check in SKILL.md refers to the official Shopify theme linter.
  • [PROMPT_INJECTION]: The skill handles external store data via Liquid objects, which is a necessary surface for theme development.
  • Ingestion points: Shopify global objects such as product, customer, cart, shop, and collection are processed in SKILL.md templates.
  • Boundary markers: The skill uses standard Liquid output tags {{ }} for data interpolation, though it does not explicitly warn against embedded instructions in these fields.
  • Capability inventory: The skill includes shell command execution for validation purposes.
  • Sanitization: Liquid filters such as strip_html are documented and available for use within the templates.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 04:19 AM
Security Audit — agent-trust-hub — liquid-themes