Skills
skills/finsilabs/awesome-ecommerce-skills/shopify-checkout-extensions/Gen Agent Trust Hub

shopify-checkout-extensions

Pass

Audited by Gen Agent Trust Hub on Mar 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it processes external data that could influence agent behavior.
  • Ingestion points: useSettings() and useCartLines() hooks in SKILL.md retrieve configuration and cart data.
  • Boundary markers: No delimiters or "ignore embedded instructions" warnings are present in the code snippets.
  • Capability inventory: applyCartLinesChange() and applyMetafieldsChange() in SKILL.md allow the extension to modify the cart and metadata.
  • Sanitization: No explicit sanitization or validation of input data is demonstrated in the provided examples.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 16, 2026, 12:05 PM