skills/leynier/alera/alera-emulator/Gen Agent Trust Hub

alera-emulator

Pass

Audited by Gen Agent Trust Hub on Jul 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill acts as a wrapper for the alera CLI tool, allowing the agent to discover, attach to, and automate Android and iOS emulators. It provides structured access to subcommands for device lifecycle management and input simulation.
  • [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface because it enables the agent to ingest untrusted data from mobile application interfaces and system logs, which could contain instructions designed to bypass agent constraints.
  • Ingestion points: Accessibility and UI data via alera emulator snapshot and device logs via alera emulator logcat as defined in SKILL.md.
  • Boundary markers: Present. The 'Boundaries' section in SKILL.md explicitly instructs the agent to treat application input as user-visible behavior only and prohibits executing destructive forms or account changes without explicit user permission.
  • Capability inventory: The agent can simulate normalized touch input (tap, gesture), inject text (type), manage app lifecycles (install, launch), and modify system-level settings (permission) in SKILL.md.
  • Sanitization: Absent. The instructions do not specify any sanitization or filtering of the content retrieved from the emulator (snapshots or logs) before the agent processes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 28, 2026, 10:34 PM