ClawHub
Back to skill

Security audit

feishu-message-group-whitelist

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Feishu group-chat keyword filter with disclosed message matching and no executable code, credentials, persistence, or hidden data flow.

Before installing, confirm the whitelist keywords are appropriate and keep config/whitelist.txt populated. If you expect an empty whitelist to mean no replies, change the documented fail-open behavior before use. Notify or obtain consent where group-message inspection is regulated or sensitive.

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 (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The documented trigger examples are broad enough to match ordinary group-chat behavior, which can cause the bot to activate in many more conversations than users may reasonably expect. In a group-chat setting, this increases the chance of unnecessary monitoring and responses, potentially exposing message content to downstream agent processing and creating privacy and misuse risks.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill description explains filtering logic but does not clearly warn that the bot inspects all incoming group message content to decide whether to respond. This missing disclosure can mislead deployers and participants about the monitoring behavior, increasing privacy, compliance, and consent risks when used in workplace or multi-user chat environments.

Static analysis

No suspicious patterns detected.