moonpay-swap-tokens
Pass
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill depends on the execution of the 'mp' (MoonPay) command-line utility. The safety of the operation depends on the integrity and correct installation of this tool in the host environment.
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection (Category 8). It instructs the agent to interpolate user-provided parameters such as wallet names, chain identifiers, and blockchain token addresses directly into shell command templates.
- Ingestion points: Parameters like '--wallet', '--chain', '--from-token', and '--from-amount' in the SKILL.md file.
- Boundary markers: The skill lacks explicit instructions or markers to sanitize or validate user input before placing it into the CLI commands.
- Capability inventory: The skill has the capability to execute system commands through the 'mp' CLI to perform financial transactions.
- Sanitization: No sanitization logic or validation steps for external input are documented within the skill's instructions.
Audit Metadata