maiat-trust-check
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes natural language fields like 'verdict' and 'summary' from the Maiat API, which are used to guide the agent's decision to proceed with financial transactions. Ingestion points: JSON responses from 'app.maiat.io'. Boundary markers: None present to distinguish API content from instructions. Capability inventory: Influences downstream swap operations such as 'moonpay-swap-tokens'. Sanitization: No validation of API-provided strings is described.
- [EXTERNAL_DOWNLOADS]: Prerequisite steps require the user to install the '@moonpay/cli' package from the NPM registry.
- [COMMAND_EXECUTION]: The skill instructions include the use of 'curl' for API interaction and the 'mp' CLI for wallet management and network requests.
Audit Metadata