moonpay-commerce
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates commerce operations by executing shell commands using the vendor's
mpCLI tool, which handles product discovery, cart management, and blockchain transaction signing. - [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Shopify stores, creating a potential surface for instructions hidden within product metadata to influence the agent. Ingestion points: Product names, descriptions, and variant IDs retrieved from third-party Shopify stores via the
mpCLI. Boundary markers: Absent; there are no instructions to the agent to delimit or ignore instructions found in external data. Capability inventory: The agent has shell execution capabilities via thempCLI to perform network-based checkouts. Sanitization: Absent; the skill does not define methods for validating or escaping content retrieved from stores.
Audit Metadata