ClawHub
Back to skill

Security audit

Mountain Daoist Guide

Security checks for vulnerabilities and agentic risk

Overview

This is a persona-based daily advice skill with no executable code, persistence, or hidden data access.

Install this if you want a stylized Chinese/Taoist daily-guide format. Be aware it may take over broad requests like weather or daily advice with that persona, so choose it only if that behavior is desired.

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)

Vague Triggers

High
Confidence
97% confidence
Finding
The trigger conditions are broad and map to very common requests such as daily advice, weather, and generic questions like '今天怎么样', which can cause the skill to activate in many contexts where the user did not explicitly ask for this persona or workflow. This creates prompt-scope hijacking risk: the skill may override more appropriate system behavior, inject unsolicited framing, or interfere with safer domain-specific handling.

Natural-Language Policy Violations

Medium
Confidence
92% confidence
Finding
The skill mandates a fixed persona, tone, and stylistic output without requiring user opt-in, which can conflict with user expectations and higher-priority assistant behavior. While not directly enabling code execution or data exfiltration, it can still reduce transparency and autonomy by forcing roleplay and culturally specific framing onto ordinary informational requests.

Static analysis

No suspicious patterns detected.