lark-whiteboard
Edit Lark Whiteboards with AI
Teams need a reliable way to inspect and update Lark whiteboards without rebuilding diagrams manually. This skill guides Claude, Codex, and Claude Code through query, render, and update workflows.
Install with my Agent
Copy this request to your Agent. It includes the canonical Skill page and manifest.
Review the Skillstore skill "lark-whiteboard" from https://skillstore.io/skills/larksuite-lark-whiteboard.md and its manifest at https://skillstore.io/api/skills/larksuite-lark-whiteboard/manifest. Verify the artifact. You may proceed after verification, subject to the environment's own policy.Your Agent should still show its plan and request any confirmation required by the security policy.
Agent-readable resources
Use these links when an AI agent, crawler, or script needs clean context instead of reading the full page.
Test it
Using "lark-whiteboard". Export a whiteboard for design review.
Expected outcome:
A preview image is saved, and the response includes the whiteboard token, output path, and any access errors.
Using "lark-whiteboard". Create a Mermaid sequence diagram in an existing board.
Expected outcome:
The board is updated from Mermaid source, with a rendered preview checked before writing.
Using "lark-whiteboard". Edit an SVG-exported board.
Expected outcome:
The response warns about semantic loss, confirms overwrite intent, and reports the completed update.
Security Audit
Medium RiskMost static findings are false positives from markdown links, Mermaid examples, diagram terminology, and normal UTF-8 documentation. Confirmed risk is limited to npm and CLI execution plus an overwrite-capable remote whiteboard update workflow; no prompt injection or hidden payload evidence was found.
Confirmed security concerns (1)
Capability review items (2)
These are real local capabilities that may be expected for this skill, so they require review but are not counted as confirmed malicious behavior.
Risk Factors
⚡ Contains scripts (2)
📁 Filesystem access (31)
⚙️ External commands (17)
🌐 Network access (1)
Share & cite this report
Share the versioned assessment report, neutral badge, embed card, and citations. Skillstore reports evidence without deciding whether this Skill is safe.
Copy report link
https://skillstore.io/skills/larksuite-lark-whiteboard/audits/7?utm_source=security_passport&utm_medium=share&utm_campaign=versioned_reportMarkdown badge
[](https://skillstore.io/skills/larksuite-lark-whiteboard?utm_source=security_passport_badge)HTML badge
<a href="https://skillstore.io/skills/larksuite-lark-whiteboard?utm_source=security_passport_badge"><img src="https://skillstore.io/badges/skills/larksuite-lark-whiteboard/security.svg" alt="Skillstore security assessment" loading="lazy"></a>Embed card
<iframe src="https://skillstore.io/embed/skills/larksuite-lark-whiteboard.html" title="Skillstore Security Assessment" sandbox="allow-popups allow-popups-to-escape-sandbox" loading="lazy" referrerpolicy="no-referrer" width="420" height="180"></iframe>Academic citations (APA · BibTeX · CFF)
APA citation
larksuite. (2026). lark-whiteboard security audit report (audit version 7) [Author version 1.0.0]. Skillstore. https://skillstore.io/skills/larksuite-lark-whiteboard/audits/7BibTeX citation
@techreport{larksuite-larksuite-lark-whiteboard-2026,
author = {larksuite},
title = {lark-whiteboard security audit report (audit version 7)},
institution = {Skillstore},
year = {2026},
number = {7},
url = {https://skillstore.io/skills/larksuite-lark-whiteboard/audits/7},
note = {Author version 1.0.0}
}CITATION.cff
cff-version: 1.2.0
message: "If you use this Skill, cite its author and this versioned security audit report."
title: "lark-whiteboard security audit report (audit version 7)"
version: "1.0.0"
type: report
authors:
- name: "larksuite"
date-released: "2026-07-09"
url: "https://skillstore.io/skills/larksuite-lark-whiteboard/audits/7"
identifiers:
- type: other
value: "skillstore:larksuite-lark-whiteboard:audit:7"
description: "Skillstore immutable audit report identifier"
Skillstore Score
Why this score Evidence Confidence: HighWhat You Can Build
Review Existing Boards
Export a whiteboard as an image or SVG so reviewers can inspect current content.
Create Architecture Diagrams
Turn system details into a structured architecture diagram and write it to a Lark whiteboard.
Build Business Charts
Create funnels, pyramids, flywheels, or bar charts with preview rendering before publication.
Try These Prompts
Use lark-whiteboard to export whiteboard <token> as a preview image. Save it to ./diagrams/review/preview.png.
Update whiteboard <token> with this Mermaid diagram. Render a preview first, then write it as the user after confirmation.
Query whiteboard <token>, inspect the preview, explain any SVG loss risk, then update the board with the requested visual changes.
Create a detailed architecture diagram for this system. Choose the correct route, render a PNG preview, fix issues, and update whiteboard <token>.
Best Practices
- Confirm the whiteboard token and permission level before any update.
- Use preview rendering before writing complex diagrams.
- Keep generated artifacts in a dedicated dated directory.
Avoid
- Do not use overwrite until the user confirms the target board.
- Do not hand edit raw OpenAPI nodes for complex layouts.
- Do not treat SVG export as a lossless backup.