ClawHub
Back to skill

Security audit

Wechat Collect

Security checks across malware telemetry and agentic risk

Overview

This skill coherently fetches a user-provided public WeChat article, creates a local brief, and archives the raw HTML as disclosed.

Install only if you are comfortable saving article briefs and raw HTML in your workspace. Avoid using it for private or sensitive pages, review the raw archive location after use, and clean up content-production/inbox/raw/wechat/ if retained copies are not needed.

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 (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding
The skill documentation declares operational behavior that reads input files and writes multiple output artifacts, but it does not declare corresponding permissions. This creates a trust and review gap: users or orchestration systems may approve or run the skill without understanding that it can modify repository state and persist fetched content to disk.

Missing User Warnings

Low
Confidence
89% confidence
Finding
The README explicitly says the skill archives raw WeChat article HTML locally, but it does not clearly warn users about retention, sensitivity, or the possibility that captured pages may contain metadata, embedded resources, or content subject to privacy and copyright constraints. This is not an exploit primitive by itself, but it is a real security/privacy weakness because users may persist scraped content longer than intended or store it in shared workspaces without understanding the exposure.

Missing User Warnings

Low
Confidence
88% confidence
Finding
The skill writes a new brief and archives raw HTML to disk, but the description does not prominently warn users about this persistence behavior. That omission can lead to accidental storage of copyrighted, sensitive, or unexpectedly large content in working directories, especially in automated pipelines where users rely on the skill description to understand side effects.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.