dingtalk-feishu-cn

• Outcome: Pass
• Latest audit: May 28, 2026, 1:56 AM
• Version:
  1.0.0

Overview

This is a documentation-only DingTalk/Feishu integration guide with expected webhook and API examples, not hidden execution or persistence.

Use this skill only with DingTalk/Feishu workspaces and channels you intend to message. Keep webhook URLs, app IDs, app secrets, and tokens out of chats and logs, test in a low-risk channel first, and confirm that any alert/report content is allowed to leave the local environment and be visible in the target enterprise chat.

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: 88% confidence
• Finding: The skill includes concrete examples for sending data to external DingTalk/Feishu webhooks and using app credentials, but it does not adequately warn that message contents may leave the local environment and reach third-party enterprise platforms. In an agent setting, this can normalize outbound transmission of potentially sensitive operational data, secrets, or user content without clear consent or data-classification guidance.

VirusTotal

63/63 vendors flagged this skill as clean.