ClawHub
Back to skill

Security audit

IceCube ZSXQ Community

Security checks for vulnerabilities and agentic risk

Overview

This skill is a Chinese-language planning guide for operating a paid Knowledge Planet community, with no hidden code, dependencies, or requested privileges.

Install only if you want help planning or operating a ZSXQ-style paid community. Review any generated marketing, payment, or publishing actions before use, and do not let the agent publish through a logged-in browser or API unless you explicitly asked it to do so.

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
  • 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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger description includes broad terms like '会员制' and '付费社区', which can appear in many unrelated user requests. This can cause unintended invocation of the skill in contexts where the user did not ask for Knowledge Planet/ZSXQ-specific guidance, leading to scope hijacking and irrelevant or commercially biased responses.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description states the skill should be used when certain Chinese terms are mentioned, which implies a language-specific routing behavior without confirming the user's preferred language. This can override user expectations and produce responses in Chinese or with Chinese-platform assumptions even when the broader conversation language or user preference differs.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.