ClawHub

飞书群Webhook发送图片

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a Feishu image-sharing helper, but it under-discloses that selected local images are uploaded to Feishu and potentially posted to a group chat.

Install only if you intend for selected images to be uploaded to Feishu/Lark and possibly posted to the configured group webhook. Verify the destination chat/webhook and avoid using confidential screenshots, documents, photos, or customer data unless your organization has approved that flow.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding
The skill clearly performs outbound network operations to Feishu APIs and a group webhook, yet the manifest does not declare corresponding permissions. This creates a transparency and governance gap: users and platform policy checks may not realize the skill can transmit data externally, increasing the risk of unintended data exfiltration or unsafe deployment.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The documentation tells users to send local images to Feishu but does not clearly state that the image contents leave the local machine and are transmitted to a third-party service and potentially a group chat. This omission can cause users to disclose sensitive screenshots, documents, or photos without informed consent, especially because the examples encourage arbitrary local file paths.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal