ClawHub

Wechat Report

Security checks across malware telemetry and agentic risk

Overview

This skill coherently collects WeChat articles and writes local reports, but users should understand its network access, browser automation, and retained local outputs before using it.

Install only if you are comfortable with the skill fetching article pages/search results, running Playwright, and storing scraped article content and metadata locally. Use a dedicated browser profile for any WeChat login or verification flow, set collect_engagement to false if you do not want browser-based engagement collection, and review/pin the external extractor dependency before relying on it.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Lp3

Medium
Category
MCP Least Privilege
Confidence
96% confidence
Finding
The skill documentation describes runtime behavior that reads input files, writes report outputs, accesses network resources to collect WeChat articles, and invokes a shell command, yet it declares no explicit permissions or capability boundaries. This creates a mismatch between stated metadata and actual behavior, which can lead to over-privileged execution, weak reviewability, and unsafe use in environments that rely on declared permissions for policy enforcement.

Missing User Warnings

Low
Confidence
83% confidence
Finding
The README documents that the skill collects multiple WeChat articles, uses browser/network-based extraction, and stores both a local markdown report and raw JSON, but it does not clearly warn users about outbound network access, persistence of scraped content/metadata, or possible privacy/compliance implications. This is a real but low-severity transparency and safe-operation issue: users may run the skill without understanding that data will be fetched from external sites and retained locally.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal