ClawHub
Back to skill

Security audit

feishuweng

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward Feishu message-sending skill, with the main caution that message text and recipient IDs are sent to Feishu.

Install this only for agents that should be allowed to send Feishu messages. Use a least-privilege Feishu app, protect and rotate APP_SECRET, set a narrow default recipient when possible, and avoid sending secrets, personal data, or regulated business content unless that Feishu tenant and app are approved for it.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill explicitly sends user-provided message content to the external Feishu API, but the documentation does not warn users that their input leaves the local agent context and is transmitted to a third party. This can cause unintentional disclosure of sensitive data, especially if an agent forwards prompts, secrets, personal data, or internal business content without clear user awareness.

Static analysis

No suspicious patterns detected.