ClawHub
Back to skill

Security audit

客观原则评价技能

Security checks for vulnerabilities and agentic risk

Overview

This is a simple markdown-only evaluation framework with no code execution, data access, persistence, or hidden authority.

Before installing, be aware that this skill may activate for broad review-style prompts and may answer with a mixed Chinese/English framing unless the user prompt makes the desired language clear. It does not appear to run code or access local/private data.

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 (2)

Vague Triggers

High
Confidence
96% confidence
Finding
The trigger description is broad enough to match many normal conversational requests such as 'what do you think of', 'review', or 'evaluate this', which can cause the skill to activate outside its intended niche. Over-broad routing increases the chance of unintended interception of user queries, response hijacking, or conflicts with more appropriate skills, especially because the skill claims authority over generic assessment tasks.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
The description and title present both Chinese and English content, but the file does not state how the response language will be chosen or that the user may opt in to a preferred language. This can create a locale/language policy issue if the skill defaults to one language or mixes languages without user choice.

Static analysis

No suspicious patterns detected.