sfcc-cartridge-development
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill includes an example for an OCAPI hook that sends customer order data, including the email address, to an external analytics endpoint.
- Evidence:
httpClient.open('POST', 'https://analytics.acme.com/orders');andcustomerEmail: order.customerEmailin theocapiHooks.jsexample withinSKILL.md. - [INDIRECT_PROMPT_INJECTION]: The skill demonstrates rendering data from content assets with output encoding disabled, creating a potential surface for injection if the source data is untrusted or compromised.
- Ingestion points: Data fetched via
ContentMgr.getContent()incontrollers/CustomPage.js(SKILL.md). - Boundary markers: No delimiters or warnings are used to separate the dynamic content from the rest of the template.
- Capability inventory: The skill enables UI rendering of dynamic HTML via ISML templates (
res.renderinSKILL.md). - Sanitization: The
contentPage.ismlexample explicitly disables sanitization using theencoding="off"attribute on the<isprint>tag.
Audit Metadata