ClawHub
Back to skill

Security audit

Ultimate Problem Solver

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language problem-solving prompt skill with no executable code, persistence, hidden data access, or installation side effects.

Install this if you want concise, structured problem-solving responses, especially in Chinese. Be aware it may activate for common requests like debugging or analysis, and it may not automatically match non-Chinese language preferences.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (3)

Vague Triggers

High
Confidence
97% confidence
Finding
The trigger list is very broad, including common phrases like '分析一下', 'debug', and 'solve this', which can match routine conversation and cause the skill to activate unexpectedly. Over-broad activation increases the chance of routing users into the wrong workflow, producing unintended advice, bypassing more appropriate specialized skills, or enabling prompt-surface abuse through unnecessary invocation.

Natural-Language Policy Violations

Medium
Confidence
89% confidence
Finding
The skill metadata and content strongly prescribe Chinese output behavior without indicating adaptation to the user's language preference. While not a direct code-execution issue, forced language behavior can degrade reliability, confuse users, and increase the risk of misunderstandings when the surrounding system or user expects another language.

Rp1

Medium
Category
MCP Rug Pull
Confidence
75% confidence
Finding
Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.

Static analysis

No suspicious patterns detected.