mobile-emulator-start

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses adb, curl, taskkill, lsof, and kill to manage local development processes and configure the Android emulator. These operations are standard for mobile development workflows.
  • [PROMPT_INJECTION]: The skill ingests terminal metadata and configuration files from the workspace, creating a surface for indirect prompt injection. * Ingestion points: Terminal metadata files in .cursor/projects/ and project configuration files (package.json, app.json). * Boundary markers: None provided. * Capability inventory: Process management (kill, taskkill), Android intent triggering (adb shell am start), and package execution (npx). * Sanitization: No specific sanitization logic is defined for the ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 05:56 AM
Security Audit — agent-trust-hub — mobile-emulator-start