The Agent Skills Directory

[UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The installation instructions in SKILL.md guide the user to download and install the ble-session-appliance CLI using npx from the @mvanhorn/printing-press-library package on NPM. This is a standard installation procedure for the vendor's ecosystem.
[COMMAND_EXECUTION]: The skill is designed to interact with a BLE device by executing the ble-session-appliance-pp-cli binary. Commands that have physical effects or configuration risks require an explicit --confirm-physical-effect flag, which serves as a safety gate.
[INDIRECT_PROMPT_INJECTION]: The skill processes telemetry data from a local JSONL file in the user's cache directory. While this data is intended to be device telemetry, it represents an ingestion point for external data into the agent's context.
Ingestion points: The telemetry latest --json command reads data from telemetry.jsonl (found in internal/device/store.go).
Boundary markers: The current implementation does not use explicit delimiters or instructions to ignore embedded commands in the telemetry data.
Capability inventory: The skill can execute CLI commands for device control and manage local session files.
Sanitization: There is no evidence of content sanitization for the telemetry data before it is presented to the agent.

ble-session-appliance