ClawHub
Back to skill

Security audit

YES.md 中文版

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language engineering quality checklist skill with broad activation, but it does not contain hidden execution, credential access, persistence, exfiltration, or destructive behavior.

Install this if you want a Chinese-language assistant style that is stricter about checking evidence, backing up files, and verifying work. Expect it to activate often during engineering tasks and to push for tool use and validation before conclusions.

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

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

The activation criteria are so broad that this skill is likely to trigger on a large share of ordinary engineering tasks, including debugging, development, configuration, deployment, and data handling. Over-broad activation can override normal task routing and inject prescriptive behavior into unrelated contexts, increasing the chance of workflow disruption, unsafe procedural mandates, or policy conflicts across many sessions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill is explicitly written to operate in Chinese and its content strongly constrains the assistant's response style and language without requiring user preference or task-context justification. Forced locale can cause misunderstandings, reduce usability for users expecting another language, and interfere with higher-priority system or user instructions in multilingual environments.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.