The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill integrates with external hardware (Plaud recorders) to ingest device data, creating a potential surface for indirect prompt injection.
Ingestion points: Data enters the agent's context through PlaudSdk.onFileList and PlaudSdk.onScanResult as documented in SKILL.md and api-reference.md.
Boundary markers: No explicit delimiters or "ignore embedded instructions" warnings are specified for the data ingested from the external hardware devices.
Capability inventory: The skill includes file-write capabilities via the exportAudio method and network upload capabilities as described in the transcription flow in references/transcription-and-tokens.md.
Sanitization: The documentation does not specify sanitization, escaping, or validation of the data (such as file names or metadata) ingested from the external recorder.

setup-plaud-flutter