e2e-testing-mobile

Pass

Audited by Gen Agent Trust Hub on May 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches the Maestro CLI installation script using curl | bash from https://get.maestro.mobile.dev. This is the official domain for the Maestro tool, a well-known service in the mobile development ecosystem.
  • [COMMAND_EXECUTION]: The skill executes shell commands to verify the presence of the Maestro CLI, EAS CLI, and to list available iOS simulators and Android emulators. It also executes Maestro tests and manages file structures within the repository.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface. It uses the Maestro MCP server to ingest the accessibility tree and view hierarchy of mobile applications. Malicious content within the application UI could potentially influence the agent's logic during test generation or the self-healing process.
  • Ingestion points: Application view hierarchy snapshots retrieved via the view_hierarchy tool (referenced in references/maestro-mcp.md and rules/spec-first-flow.md).
  • Boundary markers: None explicitly defined for the ingested view hierarchy data.
  • Capability inventory: Capability to execute shell commands, run Maestro flows, write YAML files to .maestro/, and propose source code diffs for testID attributes.
  • Sanitization: No explicit sanitization or filtering of text strings or labels retrieved from the mobile application is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 17, 2026, 04:53 AM
Security Audit — agent-trust-hub — e2e-testing-mobile