moonpay-trading-automation
Warn
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to create persistent shell scripts and schedule them using system task managers (crontab for Linux and launchd for macOS) to automate financial transactions.
- [PROMPT_INJECTION]: The skill establishes an attack surface for indirect prompt injection by interpolating user-provided data such as token addresses, amounts, and wallet names directly into generated shell scripts.
- Ingestion points: User-supplied parameters for trading strategy configuration.
- Boundary markers: None present.
- Capability inventory: File system writes, crontab and launchctl modification, and execution of the MoonPay CLI (mp).
- Sanitization: The instructions do not define validation or escaping procedures for user inputs before they are interpolated into executable shell scripts.
Audit Metadata