ClawHub
Back to skill

Security audit

董保华 · 劳动法实务

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese labor-law reference skill with broad visible triggers, but it does not run code, access data, or persist anything.

Before installing, understand that this skill may activate for common employment-law terms and gives general reference material, not legal advice. Users should verify current local laws and consult a qualified lawyer for specific disputes.

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 (4)

Vague Triggers

Medium
Confidence
94% confidence
Finding
The trigger list contains broad, common labor-law terms such as 劳动法, 辞退, 劳动争议, 试用期, and 工伤 that are likely to appear in many ordinary conversations. This can cause the skill to activate in contexts where the user did not specifically request this framework, leading to unintended routing, overreach, or inappropriate legal-style guidance.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
91% confidence
Finding
The trigger '2N' is extremely short and context-ambiguous, so it may match unrelated text, abbreviations, or formatting in ordinary conversations. This increases accidental invocation risk and weakens trigger precision, especially in multilingual or shorthand-heavy inputs.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
87% confidence
Finding
The trigger '辞退' is a common everyday term that can appear in many general discussions about employment, news, or personal situations. As a standalone trigger, it is likely to over-match and invoke the skill even when the user is not seeking this specific legal framework.

Overly Broad Trigger

Low
Category
Trigger Abuse
Confidence
84% confidence
Finding
The trigger '工伤' is short and broadly used in ordinary workplace or insurance discussions, making accidental activation plausible. In a legal-advice-adjacent skill, such imprecision can route users into a specific framework when they may only be asking for general information or non-legal help.

Static analysis

No suspicious patterns detected.