Back to skill

Security audit

ask-user-md

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese requirements-gathering prompt skill that asks structured product questions and does not request system access, credentials, persistence, or code execution.

Install this if you want a Chinese-language product requirements interview workflow. Be aware it may ask clarifying questions before implementation on broad product-building requests, so users who want immediate coding may need to redirect it.

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
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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill content is written entirely in Chinese and does not state any language negotiation behavior, so it may implicitly force Chinese output regardless of the user's language preference. This is mainly a quality and usability risk, but it can also cause misunderstanding of requirements, incorrect confirmations, and reduced user control in multilingual environments.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The activation rules are very broad and match common phrases like '我想做一个 XXX' or '帮我做个 XXX 网站/程序', which can cause the skill to trigger on many loosely related requests. This can hijack conversation flow, override more appropriate skills, and steer users into a fixed requirements-interview process even when they wanted direct implementation help or a different workflow.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.