core-bluetooth

Pass

Audited by Gen Agent Trust Hub on Sep 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a standard reference for mobile developers and does not contain executable malicious scripts or commands.
  • [INDIRECT_PROMPT_INJECTION]: The skill demonstrates processing external data from BLE characteristics. 1. Ingestion points: Data enters the application context via CBCharacteristic.value in didUpdateValueFor callbacks. 2. Boundary markers: No explicit delimiters are present for the raw BLE data stream. 3. Capability inventory: The skill updates internal state and prints parsed values to the console. 4. Sanitization: The implementation includes specific byte-parsing logic that validates the data before use.
  • [EXTERNAL_DOWNLOADS]: Reference links in the documentation point to sosumi.ai, a common mock domain for Apple-related examples. These are informational links only and do not perform any remote code execution or automated downloads.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 11, 2026, 11:13 AM
Security Audit — agent-trust-hub — core-bluetooth