Chromecast With Google Tv
AdvisoryAudited by Static analysis on Apr 30, 2026.
Overview
No suspicious patterns detected.
Findings (0)
Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.
A paired Chromecast or Android TV can be controlled from the host, including launching apps and sending media/input commands.
The skill can issue ADB shell commands to the selected device. This is expected for Google TV control, but it is still a powerful device-control interface.
def adb_shell(args: Sequence[str], device: Optional[str], timeout: int = ADB_TIMEOUT_SECONDS) -> Tuple[int, str]:
return run_adb(['shell', *args], device, timeout=timeout)Use it only with devices you own or administer, and pass the intended --device and --port when possible.
Once paired, the host can reconnect and control the TV over ADB until that pairing/debugging access is removed or disabled.
ADB wireless pairing gives the host delegated debugging/control authority over the Chromecast. This is disclosed and purpose-aligned, but it is a privileged trust relationship.
Before using this skill, you must pair your Chromecast with ADB wireless debugging
Pair only with trusted hosts and disable Wireless Debugging or revoke ADB access when you no longer need the skill.
A future version of the helper dependency could behave differently from the version reviewed here.
The YouTube helper is installed from a Go module using @latest, so the exact installed code can change over time.
go | module: github.com/nerveband/youtube-api-cli/cmd/yt-api@latest | creates binaries: yt-api
Prefer pinning the Go module to a reviewed version or verify the dependency before installing.
If the cache is stale or edited, playback/control commands could go to an unintended paired device.
The skill stores and later reuses device-selection state. This is disclosed and useful, but users should know future commands may target the cached device.
The script caches the last successful IP:PORT to `.last_device.json` in the skill folder and will use that cache if no explicit device is provided.
Specify --device and --port for important actions, and delete or check `.last_device.json` if device selection seems wrong.