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
aleraCLI 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 snapshotand device logs viaalera emulator logcatas defined inSKILL.md. - Boundary markers: Present. The 'Boundaries' section in
SKILL.mdexplicitly 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) inSKILL.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