ClawHub
Back to skill

Security audit

WeChat Store

Security checks for vulnerabilities and agentic risk

Overview

The skill is a clearly scoped WeChat Store connector with disclosed read, write, and destructive actions, though users should be cautious with its optional CLI installation command.

Install only if you trust OOMOL and your WeChat Store account connection. For first-time setup, avoid blindly piping remote install scripts into a shell; use OOMOL's documented installer or inspect and verify the script first. Review payloads carefully before approving write actions, especially product deletion, product overwrites, shipping, and after-sale decisions.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • 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)

External Script Fetching

High
Category
Supply Chain
Confidence
98% confidence
Finding

The skill instructs the agent to install software via curl ... | bash, which executes a remote script directly without prior verification or integrity checking. In an agent setting with Bash access, this creates a direct path to arbitrary code execution if the remote host, transport, or install script is compromised, and the first-time setup section makes this more dangerous because it authorizes fallback to execution on failure.

Content

Scanner excerpt · SKILL.md (reported line 80)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description says to use this skill for ANY WeChat Store request and instead of calling the API directly, which creates an overly broad activation scope. That can cause the agent to invoke a shell-capable skill on incidental mentions of WeChat Store or before clarifying user intent, increasing the chance of unnecessary tool use and unintended state-changing operations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.