ClawHub
Back to skill

Security audit

wechat-article-skill

Security checks across malware telemetry and agentic risk

Overview

This skill openly fetches WeChat public article links and extracts text, with no evidence of hidden persistence, credential theft, or destructive behavior.

Install this only if you want an agent to retrieve WeChat public article pages. Keep use limited to mp.weixin.qq.com/s/ links, avoid submitting sensitive or private URLs, and prefer adding URL validation or runtime allowlisting before broader deployment.

SkillSpector

By NVIDIA
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
93% confidence
Finding
The skill instructs the agent to perform live network access to arbitrary `mp.weixin.qq.com` article URLs via a local Python script or browser tool, but the skill declares no corresponding permissions. This creates a permission-model mismatch: the agent may fetch untrusted external content without explicit user-visible authorization boundaries, increasing SSRF-like abuse surface, privacy risk, and unintended outbound requests.

VirusTotal

53/53 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.