moonpay-missions
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the 'mp' (MoonPay) CLI tool to perform various sensitive operations, including wallet creation, token swaps, and generating buy links. These are documented as primary features of the skill for managing digital assets.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, such as trending token lists and prediction market event details, which could potentially contain adversarial content.
- Ingestion points: Data is retrieved from external sources via commands like 'mp token trending list', 'mp token search', and 'mp prediction-market market event retrieve'.
- Boundary markers: There are no explicit delimitation or sanitization instructions for the retrieved token names or market descriptions before they are presented to the user or used in subsequent steps.
- Capability inventory: The skill possesses high-privilege capabilities including executing financial transactions ('mp token swap'), signing messages ('mp message sign'), and writing to the local file system ('mp skill install').
- Sanitization: No sanitization or validation logic is defined for the external data ingested from the blockchain or APIs.
Audit Metadata