Back to skill

Security audit

xuanxuan-10agents

Security checks for vulnerabilities and agentic risk

Overview

This is a conversational Zhouyi/Feng Shui advisory skill with no code execution or persistence, though its trigger and Chinese-only persona are broad.

Install only if you want a Chinese traditional-metaphysics advisory persona. Treat its business, naming, Feng Shui, and date-selection guidance as cultural reference, not as a substitute for practical, financial, legal, or operational analysis, and avoid sharing unnecessary personal birth or founder details.

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 (3)

Vague Triggers

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger condition is extremely broad and mandatory, covering many common topics and requiring immediate activation whenever loosely related concepts appear. This can cause frequent misrouting of normal conversations into this skill, reducing user control and potentially leading the assistant to provide inappropriate mysticism-based guidance in contexts where users did not explicitly ask for it.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The skill description mandates a specific Chinese cultural and language framing without offering a language or locale choice. This can cause the system to respond in an unsuitable language or impose a culturally specific advisory mode on users who did not request it, creating usability and policy-compliance risks rather than direct security compromise.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The fixed Chinese opening line hardcodes the initial interaction language and persona without checking the user's preferred language. In multilingual environments this can confuse users, create accessibility issues, and force an unwanted cultural framing at the start of the exchange.

Content

No source excerpt is available for this finding.