ClawHub
Back to skill

Security audit

emperor-liu-bang

Security checks for vulnerabilities and agentic risk

Overview

This is a persona-style strategy advice skill with broad activation, but it does not request tools, credentials, persistence, file access, or execution authority.

Install this if you want stylized Chinese strategic advice in a Liu Bang persona. Treat business or investment recommendations as perspective only, and use qualified professional advice for legal, medical, financial, or high-stakes decisions.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

The skill content strongly constrains the assistant to a specific historical persona and Chinese-language presentation style without stating that this occurs only with user preference or consent. While not directly enabling code execution or data exfiltration, it can reduce usability, create confusion for users expecting another language, and interfere with system-level expectations for locale or accessibility.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger condition is extremely broad: it covers effectively any scenario involving strategy, decisions, management, investment, or competitive response. This can cause unintended invocation outside the user’s explicit intent, leading the assistant to adopt a rigid persona and decision-making frame in situations where neutral or specialized guidance would be safer.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.