mobile-testing

Pass

Audited by Gen Agent Trust Hub on Oct 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONPRIVILEGE_ESCALATION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes processes for interacting with and asserting the state of mobile application UIs. This represents an attack surface where untrusted data displayed by the application under test could influence agent behavior.
  • Ingestion points: UI interaction methods and assertions in references/flutter.md and references/maestro.md that read text content from the app.
  • Boundary markers: Absent; no specific instructions to ignore instructions found within app text.
  • Capability inventory: Execution of testing CLI tools (flutter, patrol, maestro), file system access for artifact/screenshot management, and network access for API seeding.
  • Sanitization: Absent.
  • [PRIVILEGE_ESCALATION]: Documentation in references/flutter.md includes a GitHub Actions configuration example that uses sudo to modify udev rules. This is a standard and necessary step for enabling KVM hardware acceleration for Android emulators on Linux-based CI runners and is consistent with the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 18, 2026, 11:08 AM