ClawHub
Back to skill

Security audit

风险评估与反例库

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only Chinese RWA/Web3 risk-assessment guide with clear anti-fraud boundaries and no evidence of hidden execution, persistence, credential access, or data exfiltration.

Before installing, note that this skill is written for Chinese-language RWA/Web3 risk review and includes China-specific compliance framing. Use it as educational risk-screening support, not as legal, financial, or investment advice.

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
92% confidence
Finding

The skill is written entirely in Chinese without offering a language option or explicitly restricting usage to Chinese-speaking users. This can cause non-Chinese-speaking operators, reviewers, or downstream agents to misunderstand risk criteria, disclaimers, and activation boundaries, which is especially problematic for a security- and compliance-adjacent skill where misinterpretation can lead to unsafe decisions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

This manifest-like JSON embeds all user-facing prompts, expected behaviors, and notes in Chinese only, which implies the skill is designed around a single language without offering a locale choice. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation unless the locale restriction is clearly documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and covers language or locale policy violations. This markdown file presents all user-facing content in Chinese and does not indicate that the skill is region-specific or that users may opt into another language, which can conflict with organizational language-choice expectations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.