ClawHub
Back to skill

Security audit

Yq Feishu Webhook Skill

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a legitimate Feishu/Lark webhook helper, but it needs review because broad triggers and weak confirmation guidance could cause unintended outbound messages or image uploads.

Install only if you intentionally want an agent to send Feishu/Lark webhook messages. Use a narrowly scoped webhook and token, prefer environment-variable secret handling over command-line token arguments, and require explicit user confirmation before any message send or image upload.

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Confidence
95% confidence
Finding
The trigger keywords are broad and include generic terms like '消息' and '通知', which can match many unrelated user requests and cause this skill to activate unexpectedly. In this skill's context, unintended invocation is more concerning because the skill is designed to send outbound webhook messages, so accidental routing could lead to unintended notifications, data disclosure to a Feishu channel, or user confusion.

Static analysis

No suspicious patterns detected.