mobile-sim-verification
Pass
Audited by Gen Agent Trust Hub on Oct 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a wide variety of shell commands for environment setup, service management, and testing. These include vendor-specific tools (
superset terminals), mobile development tools (expo,xcodebuild,simctl,maestro), and utility commands (bun,wrangler,ffmpeg,curl,pkill). - [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it is designed to ingest and analyze untrusted data from external sources.
- Ingestion points: The agent reads mobile application logs (relay logs,
/tmp/superset-eas-egress.log), simulator UI snapshots, and video recordings to verify behavior. - Boundary markers: No specific delimiters or safety instructions are provided to the agent to distinguish between data and instructions within these logs or UI elements.
- Capability inventory: The skill has extensive capabilities including shell command execution (
simctl,maestro,bun,pkill), network operations viacurl, and direct SQL database writes (insert into subscriptions). - Sanitization: There is no evidence of sanitization or filtering applied to the external log data or UI content before it is processed by the agent.
Audit Metadata