ClawHub
Back to skill

Security audit

微信公众号运营工具

Security checks across malware telemetry and agentic risk

Overview

The skill mostly matches its WeChat publishing purpose, but it needs review because it handles account credentials/session state and includes unclear high-impact access guidance.

Install only if you are comfortable giving this skill access to WeChat Official Account publishing credentials. Do not whitelist IP 112.8.202.216 unless you know and trust the runtime that controls it; prefer whitelisting your own outbound IP. Store AppSecret and saved browser state outside shared or synced workspaces, exclude them from git, restrict file permissions, and rotate the AppSecret if it may have been exposed.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (4)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The trigger words include broad everyday phrases such as '写推文', which may activate the skill outside a clearly bounded WeChat Official Account context. Mis-triggering a skill with write/network/automation capabilities can cause unintended browsing, content generation, publication steps, or requests for credentials in unrelated conversations.

Missing User Warnings

Medium
Confidence
94% confidence
Finding
The skill instructs users to save browser login state and store AppID/AppSecret credentials in the workspace, but it provides no security controls, storage hardening guidance, access restrictions, or handling requirements for sensitive tokens and session files. In this context, saved auth state and credential files could enable account takeover, unauthorized publishing, or API abuse if the workspace is exposed or reused by other tools/skills.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The guide tells users to store the WeChat AppSecret in a plaintext JSON file but does not warn them to restrict file permissions, avoid committing it to source control, or use a safer secret-management mechanism. Because this skill automates official-account publishing and uses high-value API credentials, accidental disclosure could let an attacker access or abuse the linked公众号 API capabilities.

Missing User Warnings

Medium
Confidence
84% confidence
Finding
The document instructs users to place the WeChat app secret directly in a URL query string when requesting an access token, but it does not warn that URLs may be logged by shells, proxies, browser history, or monitoring systems. In a skill that automates publication workflows, this increases the chance that long-lived credentials are exposed during normal use.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.