ClawHub
Back to skill

Security audit

微信公众号文章发布

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed WeChat article-drafting workflow that saves a draft to the user's logged-in account, with no bundled code or persistence.

Before using this skill, be aware that it is intended to operate in a logged-in WeChat public account and save generated content as a draft. Review the article title, body, and cover image before allowing the final save, especially for business or public-facing accounts.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly instructs the agent to click the WeChat '保存' button and save content into the user's公众号 draft box, which is a state-changing action on the user's authenticated account. Because the workflow contains no explicit user confirmation or warning immediately before the save step, an agent following these instructions could modify account content without clear, contextual consent, increasing the risk of unintended publication workflow changes or storage of unwanted material.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.