ClawHub
Back to skill

Security audit

WeChat Official Account

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for managing a WeChat Official Account, but it includes unverified remote installer commands that could execute changing code on a user's machine.

Review this skill before installing. It can publish, send, modify, and delete WeChat Official Account content through a connected OOMOL account, so use it only with an account you intend the agent to manage. Install the oo CLI manually from a trusted source and avoid letting an agent run the curl|bash or irm|iex installer commands unless you have reviewed and trust the installer.

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
96% confidence
Finding

The skill instructs users to install software via curl ... | bash, which executes a remote script fetched at runtime without verification, pinning, or integrity checks. If the host, transport, distribution pipeline, or script content is compromised, this can lead to arbitrary code execution on the user's machine with the user's privileges.

Content

Scanner excerpt · SKILL.md (reported line 96)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The description says to use this skill for "ANY WeChat Official Account request" and "Whenever a task involves WeChat Official Account," which is a very broad trigger without clear constraints or exclusion examples. This can overlap with many ordinary WeChat-related tasks and does not specify boundaries for when the skill should or should not activate.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.