mobile-platform-native-capabilities-integrate

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE_AND_EXFILTRATION]: The skill provides instructions for accessing sensitive user data, including contacts, calendar events, geographic location, and biometric authentication status. These operations are performed using the official lightning/mobileCapabilities module and are gated by the standard mobile operating system permission flows. This access is consistent with the skill's primary purpose of providing mobile-native functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill enables an agent to process data from untrusted external sources, such as barcodes, scanned document text, and NFC tag payloads.
  • Ingestion points: Data enters the environment through BarcodeScanner.scan(), DocumentScanner.scan(), and NfcService.read().
  • Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions for the data read from these sensors.
  • Capability inventory: The skill allows for writing data back to the device (e.g., ContactsService.putContact, CalendarService.addEvent) and initiating payments via PaymentsService.collectPayment.
  • Sanitization: The instructions do not explicitly detail sanitization of the sensor-derived content before it is interpolated into subsequent actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 12:17 AM
Security Audit — agent-trust-hub — mobile-platform-native-capabilities-integrate