ClawHub
Back to skill

Security audit

emperor-liu-xiu

Security checks for vulnerabilities and agentic risk

Overview

This is a persona-style strategy advice skill with no code, tool use, persistence, credential access, or hidden execution.

Install only if you want a historical-emperor persona to shape strategy and management advice. Treat its investment, business, medical, or legal-adjacent output as general perspective, not professional 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 (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The trigger condition is phrased so broadly that it can match 'any scenario needing strategy/decision/management advice,' which risks unintended invocation across many unrelated user requests. Over-broad activation can cause the agent to assume this persona and decision style when not explicitly requested, potentially overriding more appropriate task-specific behaviors or introducing authoritative strategic advice in sensitive contexts.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.