The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill implements logic to read data from external NFC tags, which serves as an ingestion point for untrusted content.
Ingestion points: NFC detection delegates in SKILL.md and payload processing in references/nfc-patterns.md read data directly from external tags.
Boundary markers: The instructions do not include the use of delimiters or clear instructions to the agent to treat the ingested tag data as untrusted content.
Capability inventory: The skill demonstrates capabilities for hardware interaction, including writeNDEF and sendCommand for APDU instructions, which are low-level operations.
Sanitization: The provided code snippets do not include logic for sanitizing or validating the contents of the NFCNDEFPayload before it is consumed by the application.

core-nfc