ClawHub
Back to skill

Security audit

共建社区运营框架

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese-language educational framework for Web3 community operations and does not include code execution, credential access, persistence, or hidden data flows.

Use this as educational community-operations guidance, especially for Chinese Web3 contexts. Do not treat it as legal, financial, investment, token-issuance, fundraising, or smart-contract advice; those topics require current compliance review and specialist support.

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 (3)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The manifest description explicitly states the skill is aimed at Chinese-speaking Web3 creators and entrepreneurs. Under the policy rule, a fixed language/locale constraint is a finding unless the skill offers user opt-in or clearly documents a justified regional constraint; this file does not provide such a choice or justification for restricting usage to Chinese-language users.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The test prompts define activation largely through broad natural-language examples such as '消费即投资', '共建者', and '四融' without encoding stricter decision boundaries inside the file. That makes routing easier to spoof or over-trigger: adjacent requests involving token issuance, contribution accounting, or compliance could be incorrectly captured by this skill, causing unsafe or out-of-scope guidance to be given before proper specialist or compliance skills are invoked.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file presents all user-facing content in Chinese, including headings, labels, and evaluation notes. Under the policy rules, forcing a specific language without user opt-in or a documented justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.