Back to skill

Security audit

Shike Zhugeliang Perspective

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Zhuge Liang persona/perspective skill with no code execution, data access, persistence, or hidden system changes.

Installation is reasonable if you want a Chinese-language Zhuge Liang-style strategic perspective. Be aware that broad terms like Zhuge Liang, Kongming, and Wolong may cause the skill to activate more often than intended in systems that auto-detect skill triggers.

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
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 (2)

Vague Triggers

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill declares broad trigger words using well-known names and aliases like '诸葛亮', '孔明', and '卧龙' without defining stricter activation boundaries. This can cause unintended activation during ordinary conversation, leading to prompt-routing confusion, incorrect persona injection, or accidental disclosure of the skill behavior in unrelated contexts.

Content

No source excerpt is available for this finding.

Vague Triggers

Low
Category
Not specified by scanner
Confidence
86% confidence
Finding

The usage examples rely on natural-language phrases such as '/诸葛亮' and '用诸葛亮视角...' but do not specify how these differ from normal user discussion. In systems that auto-detect triggers from free text, this ambiguity increases the chance of accidental activation and unintended persona switching.

Content

No source excerpt is available for this finding.