bigcommerce
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of external data from BigCommerce, creating an attack surface for indirect prompt injection where instructions could be hidden in ecommerce data.
- Ingestion points: The skill provides instructions for the agent to fetch data using
apideck.ecommerce.orders.list,products.list, andcustomers.listinSKILL.md. - Boundary markers: Absent. The provided examples do not include specific delimiters or instructions to the agent to treat external content as untrusted.
- Capability inventory: The skill examples demonstrate reading and writing ecommerce data via the Apideck API and using a Proxy API for arbitrary BigCommerce endpoints.
- Sanitization: Absent. The skill does not provide logic for sanitizing or validating data returned from the external API before it is processed by the agent.
Audit Metadata