ClawHub
Back to skill

Security audit

祝福

Security checks for vulnerabilities and agentic risk

Overview

This skill is a clearly described WeChat greeting composer and sender that requires preview plus confirmation before delivery.

Install only if you intend to let the agent send or schedule WeChat messages through your configured operations gateway. Review previews carefully, especially recipient lists and scheduled times, before confirming delivery.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • 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)

Lp3

Medium
Category
MCP Least Privilege
Confidence
88% confidence
Finding
The skill declares access to sensitive environment variables and an authenticated operations endpoint, and it instructs use of a Python script that can send messages over the network, but it does not declare explicit permissions. This creates a transparency and governance gap: the skill can perform externally impactful actions and use credentials without a clear permission model, increasing the risk of unauthorized message delivery or misuse if invoked unexpectedly.

Static analysis

No suspicious patterns detected.