Skills
Navigate
skills/sensliao/claude-code-setting/qa-mobile-native-e2e/Gen Agent Trust Hub

qa-mobile-native-e2e

Fail

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill references the official Maestro installation command that pipes a remote script to bash (curl -fsSL https://get.maestro.mobile.dev | bash). This source is recognized as a well-known technology service.
  • [EXTERNAL_DOWNLOADS]: Fetches installation and configuration data from get.maestro.mobile.dev.
  • [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by ingesting external project files.
  • Ingestion points: Processes project configuration files (such as AndroidManifest.xml, build.gradle, package.json, and pubspec.yaml) and user-defined test flows in .maestro/*.yaml.
  • Boundary markers: The instructions lack explicit markers to delimit untrusted input or warn the agent against embedded commands.
  • Capability inventory: Employs the Bash tool to run CLI-based tests according to the detected project structure.
  • Sanitization: No logic for sanitizing or validating the contents of external YAML flow files is described.
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 16, 2026, 09:28 AM