ClawHub
Back to skill

Security audit

Guanxi

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only WeChat message-drafting skill with no code execution, persistence, or hidden access behavior.

Install only if you want China/WeChat-specific communication help. Treat generated messages as drafts: confirm names, roles, dates, holiday details, red packet amounts, and tone before sending, especially in sensitive business or personal contexts.

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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
79% confidence
Finding

The description says this is 'the only AI skill built specifically for WeChat communication in China' and frames outputs around Chinese business etiquette and hierarchy as the default behavior. While the skill is clearly China-focused, the wording does not explicitly present this locale-specific mode as an opt-in or clearly bounded regional specialization for all uses, which can create a language/locale policy concern.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.