feishu-create-openclaw-app

• Outcome: Review
• Latest audit: May 29, 2026 at 9:24 PM UTC
• Version:
  1.0.1

Overview

This skill is a legitimate Feishu app setup helper, but it automates broad enterprise permissions and tells the agent to reveal a full app secret in chat.

Install only if you are authorized to administer Feishu/Lark enterprise apps. Review and reduce the permission list before applying it, require explicit approval before granting permissions, and avoid letting the agent print the App Secret into chat; copy it directly into a secure configuration or rotate it if it has already been exposed.

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 (3)

Missing User Warnings

Medium

• Confidence: 97% confidence
• Finding: The skill explicitly instructs the agent to reveal the App Secret and display the full credential back to the user, but provides no safeguards for secret handling, redaction, or confirmation. Secrets shown in chat transcripts or logs can be copied, retained, or exposed beyond the intended recipient, enabling unauthorized access to the Feishu application.

Missing User Warnings

Medium

• Confidence: 94% confidence
• Finding: The skill bulk-imports a wide set of tenant and user permissions, including messaging, files, documents, HR file download, and spreadsheet access, without any user-facing explanation of scope or least-privilege justification. This can cause over-privileged app creation and unnecessary access to sensitive enterprise data if the app or its credentials are later misused or compromised.

Ssd 3

High

• Confidence: 99% confidence
• Finding: The instructions direct the agent to extract the App Secret, reveal it via the UI, and include the full secret in final output. In an agent setting, this creates a direct secret-exfiltration path into conversational output, logs, and any downstream integrations, substantially increasing the risk of credential compromise.

VirusTotal

64/64 vendors flagged this skill as clean.