ClawHub
Back to skill

Security audit

WeChat Official Account Draft Management

Security checks across malware telemetry and agentic risk

Overview

This is a disclosed WeChat Official Account draft-management tool, but publish and delete actions should be used carefully.

Install only if you intend to let this skill manage a WeChat Official Account. Protect WECHAT_APPSECRET and ~/.config/channel/access_token.json, review media IDs before running publish or delete, and only pass article or image files you are comfortable uploading to WeChat.

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
95% confidence
Finding
The skill declares environment variables for WeChat credentials and its documentation demonstrates file, network, and shell-driven operations, but it does not declare explicit permissions for those capabilities. This creates a transparency and governance gap: users and reviewers may not understand that the skill can access secrets, local files, and external APIs, increasing the risk of over-privileged execution and accidental secret exposure.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The documentation includes a delete command for drafts without clearly warning that deletion is destructive and may be irreversible from the tool's perspective. This raises the likelihood of accidental content loss, especially in automation or when operators copy example commands without understanding the consequence.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The delete command performs an irreversible remote deletion immediately after receiving a media_id, without any confirmation step or safety interlock. In a CLI or agent context, this makes accidental or induced destructive actions much more likely, especially when arguments can be supplied by another system or user prompt.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.