ClawHub
Back to skill

Security audit

Liubang Think Partner

Security checks for vulnerabilities and agentic risk

Overview

This is a text-only leadership and strategy thinking skill with clear limits and no code, data access, persistence, or external service behavior.

Before installing, users should treat this as a historical-strategy reflection aid, not as professional HR, legal, safety, compliance, financial, or investment advice. Its main practical caveat is possible overuse on general management questions, not unsafe system behavior.

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 (1)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
76% confidence
Finding

The 'When to Use' section lists trigger-style questions such as '该进攻还是该防守，方向怎么定？' and '选合作伙伴/合伙人，看什么？' that are common managerial phrases and could overlap with many ordinary conversations. Although the skill is themed around Liu Bang's perspective, this section does not clearly state boundaries or negative examples for when these prompts should not activate the skill.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.