shopify-checkout-extensions
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the creation of extensions that ingest and process untrusted data from Shopify storefronts, which could potentially serve as a vector for instructions targeting the agent or platform.
- Ingestion points: Extensions read data from the checkout context using hooks like
useCartLines,useMetafield, and theRunInputparameter in Shopify Functions as seen inSKILL.md. - Boundary markers: The examples do not demonstrate the use of delimiters or explicit instructions to ignore potentially malicious content within user-supplied strings such as gift messages or product metadata.
- Capability inventory: The skill demonstrates writing to the order context via
applyMetafieldsChangeand modifying cart state viaapplyCartLinesChangeinSKILL.md, providing a state-changing capability based on untrusted inputs. - Sanitization: Input data from the cart or buyer identity is processed directly without explicit sanitization or validation logic in the provided code snippets.
Audit Metadata