The Agent Skills Directory

[SAFE]: The skill provides legitimate development patterns for mobile hardware access, focusing on industry-standard libraries and proper resource cleanup to prevent memory leaks and battery drain.
[INDIRECT_PROMPT_INJECTION]: The skill defines patterns for ingesting data from external hardware sources (BLE peripherals and NFC tags), which represents an inherent attack surface for indirect prompt injection if that data is later processed by an AI agent.
Ingestion points: examples/core.md (reading GATT characteristics via readCharacteristicForService) and examples/nfc.md (reading NDEF messages via getTag).
Boundary markers: The provided examples focus on hardware interaction and do not implement delimiters or boundary markers for the data extracted from the hardware.
Capability inventory: The skill facilitates reading and writing to GATT characteristics and NDEF records.
Sanitization: The skill demonstrates standard data conversion (Base64 and UTF-8 decoding) but does not include explicit content sanitization or validation logic.

mobile-hardware-ble-nfc