JoyIn Robot Control
v1.1.0Control JoyIn AI robots (W-1 Walle / M-1 Mini) — movement, follow, photo, video, live stream, TTS, agent config, and device status via OpenAPI.
⭐ 0· 167·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Benign
high confidencePurpose & Capability
Name/description match the contents: a Python CLI that calls a JoyIn OpenAPI. Required binary (python3) and environment variables (API base, auth key, device SN) are sensible and necessary for the described robot control functionality.
Instruction Scope
SKILL.md instructs the agent to run the included Python script and to perform a preflight check before commands. The instructions reference only the declared env vars and the included example config; they do not request unrelated files, system secrets, or transmission to unexpected endpoints.
Install Mechanism
No install spec or external downloads; the skill is instruction-only with a bundled Python script that uses only the standard library. Nothing is fetched from arbitrary URLs or written to system locations during install.
Credentials
The skill requests a single service credential (JOYIN_AUTH_KEY) plus API base and device identifiers — all directly relevant to calling the robot API. The number and naming of env vars are proportional to the functionality.
Persistence & Privilege
The skill does not request always:true and does not modify other skills or global agent settings. disable-model-invocation is false (normal), which allows autonomous invocation but is not combined with suspicious access patterns.
Assessment
This skill appears coherent with its stated purpose, but before installing: 1) verify JOYIN_API_BASE points to the official JoyIn API (avoid test/personal hosts unless you intend to use them); 2) keep JOYIN_AUTH_KEY private — prefer injecting it from a secure env/provider rather than storing plaintext in openclaw.json; 3) consider using a scoped/limited token for robot control and rotate it if possible; 4) test first with a non-production/test device to confirm behavior (and always run the provided preflight check before issuing movement commands); and 5) be aware the agent can invoke this skill autonomously (platform default), so restrict access to the skill only to trusted agents/users if physical safety is a concern.Like a lobster shell, security has layers — review code before you run it.
latestvk97d6dqcghwjjqhex6twe4kcen82wsed
License
MIT-0
Free to use, modify, and redistribute. No attribution required.
Runtime requirements
Binspython3
EnvJOYIN_API_BASE, JOYIN_AUTH_KEY, JOYIN_DEVICE_SN
Primary envJOYIN_AUTH_KEY