skills/terminalskills/skills/maestro/Gen Agent Trust Hub

maestro

Fail

Audited by Gen Agent Trust Hub on Sep 21, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: Fetches and executes an installation script from the official domain at https://get.maestro.mobile.dev using a shell pipe (curl | bash). This is the documented setup procedure for the Maestro testing framework.
  • [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it processes test definitions and environment variables that drive automated interactions.
  • Ingestion points: Processes Maestro YAML flow definitions and environment variables (${EMAIL}, ${PASSWORD}) interpolated into test steps in SKILL.md.
  • Boundary markers: No specific delimiters or "ignore instructions" warnings are used around flow definitions.
  • Capability inventory: Includes execution of the Maestro CLI, shell commands for installation and test execution, and interactive mobile device operations (launching apps, tapping, and entering text).
  • Sanitization: The skill does not implement sanitization or validation for the content of environment variables before they are used in automated test flows.
Recommendations
  • HIGH: Downloads and executes remote code from: https://get.maestro.mobile.dev - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Sep 21, 2026, 03:35 AM
Security Audit — agent-trust-hub — maestro