moonpay-feedback

Pass

Audited by Gen Agent Trust Hub on Mar 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the mp command-line interface, which is the official tool belonging to the author, MoonPay.
  • [PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection by taking user-provided feedback messages and interpolating them into shell commands. This is an essential feature of the skill's purpose. 1. Ingestion points: The user-provided message in SKILL.md. 2. Boundary markers: The message is encapsulated in double quotes within the mp feedback create command template. 3. Capability inventory: Execution of the mp CLI tool. 4. Sanitization: No explicit sanitization or validation of the message content is performed within the markdown instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 21, 2026, 10:25 PM