ClawHub
Back to skill

Security audit

WeChat Article Exporter

Security checks across malware telemetry and agentic risk

Overview

This WeChat article screenshot skill mostly does what it claims, but it uses undisclosed browser anti-detection and security-disabling settings that users should review before installing.

Install only if you are comfortable with a Playwright-based WeChat exporter that disguises automation and disables some browser protections. Use it in an isolated workspace, avoid sensitive browser profiles, and confirm that automated capture of the target articles complies with the site and account rules.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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
Findings (2)

Context-Inappropriate Capability

Medium
Confidence
96% confidence
Finding
This code contains extensive anti-bot and anti-detection measures that go well beyond ordinary screenshot automation, including masking webdriver signals, spoofing browser properties, and disabling multiple browser safeguards. In the context of a WeChat article exporter, this materially increases the ability to bypass platform defenses and abuse the tool for scraping or evasive access, even if the likely author intent is functionality rather than overt malice.

Vague Triggers

Medium
Confidence
90% confidence
Finding
The trigger phrases are broad enough to match common user requests like generic screenshot/export tasks, which can cause the skill to activate when the user did not explicitly intend to use a WeChat article exporter. In an agent setting, overly broad routing increases the chance of unintended tool execution and processing of untrusted URLs or content without sufficiently clear user consent.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.