ClawHub
Back to skill

Security audit

天衡命名宗师

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese personal naming skill with disclosed information requests and no code, persistence, network access, or privilege-seeking behavior.

Before installing, understand that the skill may ask for personal naming details such as birth date, birth time, gender, surname, generation-name rules, and optional parent names for conflict checks. Install it only if you are comfortable sharing that context in the conversation.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Confidence
92% confidence
Finding
The trigger text is broad enough to activate on almost any Chinese naming-related request, including generic 'Chinese name' or 'name meaning' queries. Overly broad activation can cause the agent to intercept requests outside its narrow intended scope, leading to misrouting, unnecessary collection of sensitive personal data like birth date and birth time, and reduced user control over which skill handles the request.

Natural-Language Policy Violations

Medium
Confidence
95% confidence
Finding
The framework is written to produce Chinese-language naming outputs by default and does not provide any mechanism to detect, preserve, or ask for the user's preferred language. This can cause unwanted disclosure or exclusion in multilingual contexts, and may lead the agent to ignore explicit user language expectations, reducing usability and trust.

Static analysis

No suspicious patterns detected.