shoplazza-orders
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill interacts with external order data (such as customer notes and shipping details) via the Shoplazza API, which serves as a potential ingestion point for untrusted content. This risk is effectively mitigated by the skill's instructions to always use
--dry-runfor state-changing operations, restate planned actions for user review, and never fabricate identity or financial data. - [SAFE]: The skill uses the official shoplazza CLI and addresses resources within the vendor's own infrastructure. The documentation explicitly warns against inventing data and mandates human-in-the-loop verification for sensitive actions like refunds or order cancellations.
Audit Metadata