ClawHub
Back to skill

Security audit

feishuweng

Security checks across malware telemetry 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

By NVIDIA
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.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal