lark-wiki-writer

• Outcome: Review
• Latest audit: May 29, 2026 at 9:23 PM UTC
• Version:
  1.0.1

Overview

The skill appears to be a legitimate Lark/Feishu automation, but it asks for sensitive credentials and can send or modify business content without enough privacy and scoping safeguards.

Install only if you are comfortable giving the agent access to the relevant Lark/Feishu app credentials and workspace content. Use a least-privilege app, avoid pasting secrets into chat, confirm the exact target space or document before writes, and rotate or revoke credentials after testing.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

• Confidence: 89% confidence
• Finding: The skill instructs users to supply App ID, App Secret, space identifiers, and document content for operations that call remote Lark APIs, but it does not clearly disclose the data flow or privacy/security implications of sending that material to an external service. This can lead users to paste sensitive content or credentials without understanding that the skill will transmit them off-platform, increasing the risk of inadvertent data exposure.

VirusTotal

64/64 vendors flagged this skill as clean.