ClawHub

YBoard Operator

v0.1.0

Operate yboard.online to navigate scenes, edit text fields, switch modes, and add clear, text-free hero visuals following yboard illustration rules.

⭐ 1· 1.6k·1 current·1 all-time
byAlex M@zonder
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
Name and runtime instructions both describe operating yboard.online (navigating scenes, editing fields, drawing images). There are no unrelated env vars, binaries, or installs requested, so requested capabilities match the stated purpose.
✓
Instruction Scope
SKILL.md gives concrete, limited UI automation steps (attach Browser Relay to the yboard tab, switch modes, edit fields, add images, QA). It does not instruct reading unrelated files, accessing unrelated endpoints, or exfiltrating data. Note: the skill requires the agent to control a browser tab (Browser Relay), so whatever is present in that tab will be accessible to the agent — this is expected for a web-UI operator but is the primary privilege the skill needs.
✓
Install Mechanism
No install spec and no code files — instruction-only. Nothing is downloaded or written to disk by the skill itself.
✓
Credentials
No environment variables, credentials, or config paths are requested. The only external dependency implied is an attached Browser Relay session for the specific yboard tab; no undeclared secrets or unrelated service credentials are demanded.
✓
Persistence & Privilege
always is false and the skill does not request persistent/system-wide changes. Model invocation is allowed (the platform default); there is no additional privileged presence or modifications to other skills.
Assessment
This skill is instruction-only and appears coherent for the task of editing yboard.online. The main risk is that it requires the agent to control a browser tab via Browser Relay — anything visible in that tab can be read and changed by the agent. Before installing or invoking: (1) make sure no sensitive data is open in the yboard tab, (2) back up important yboard content you don't want changed, and (3) if you don't want the agent to run autonomously, disable autonomous invocation for skills or only invoke it manually.

Like a lobster shell, security has layers — review code before you run it.

latestvk976stzx6b13bt32dbmbc41msx8006q1

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments