ClawHub
Back to skill

Security audit

First Principles Thinking

Security checks for vulnerabilities and agentic risk

Overview

This is a simple thinking-framework skill that does not request access to files, credentials, tools, network, or persistent system changes.

Install this if you want the agent to challenge assumptions and ask clarifying questions before proposing solutions. Users who prefer direct answers or non-Chinese interaction should be aware the instructions are Chinese-first and may make the assistant more deliberative.

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 (2)

Vague Triggers

Medium
Confidence
92% confidence
Finding
The trigger description is broad enough to activate on many normal requests involving analysis, questioning assumptions, or asking for better approaches. This can cause the skill to intervene when not needed, potentially overriding user intent, adding friction, or steering conversations away from direct answers, which is a prompt-scope security and reliability issue even without clearly malicious intent.

Natural-Language Policy Violations

Medium
Confidence
97% confidence
Finding
The skill content is written entirely in Chinese and implicitly directs interaction in Chinese without giving the user a choice or stating a justified locale restriction. In a multilingual assistant, this can degrade usability, cause unintended language switching, and create confusion that weakens safe execution and user control, though the impact is limited compared with direct security compromise.

Static analysis

No suspicious patterns detected.