Back to skill

Security audit

Universal Expert

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language analysis helper that asks the agent to verify facts before giving expert-style answers, with no hidden code, persistence, or credential handling found.

Install this if you want a Chinese-oriented expert analysis workflow that will usually browse or search before answering. Review before using it for private, account-based, legal, financial, or safety-critical tasks, and require confirmation before any tool accesses sensitive or logged-in data.

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
  • 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 (1)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest description and trigger rules are written as mandatory Chinese phrases such as "深度分析", "完整分析", and "全面评估", and the file does not offer an alternative language option or explain a justified locale restriction. This creates a language/locale policy issue because activation appears to depend on a specific language without user opt-in.

Content

No source excerpt is available for this finding.