ClawHub

微信文章格式转换

Security checks across malware telemetry and agentic risk

Overview

This skill appears to do what it claims: fetch WeChat articles and save converted copies locally, with no evidence of hidden credential use or destructive behavior.

Install only if you are comfortable with a local Python skill making web requests to WeChat and saving article files to your Desktop. Review the output location during batch or HTML export because it may create many files, and use a trusted Python environment for the undeclared dependencies.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (3)

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill performs network access and local file writes/reads but does not declare any permissions, which undermines user/admin visibility into what the skill can do. In this context, the behavior is expected for fetching and exporting articles, but the lack of explicit permission declaration still creates a real security and governance gap because the skill downloads remote content and saves files to the user's Desktop.

Vague Triggers

Medium
Confidence
84% confidence
Finding
The trigger phrases include broad natural-language requests such as '帮我转这篇文章' and '保存微信文章', which can match ordinary conversation without requiring a clearly scoped WeChat URL or explicit invocation. This increases the chance of unintended activation, which could cause unsolicited network requests and local file creation from content the user did not clearly intend to process.

Vague Triggers

Medium
Confidence
87% confidence
Finding
The trigger section repeats ambiguous activation phrases and does not establish strong scope boundaries, reinforcing the risk of accidental invocation. In this skill, unintended activation is more concerning because the resulting workflow performs external requests and stores fetched content locally, potentially exposing browsing intent or creating unwanted files.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal