Back to skill

Security audit

Zhang Xiaolong Perspective V2

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only persona skill for product thinking, with no code execution, data access, persistence, or hidden install behavior.

Install only if you want a Chinese-language Zhang Xiaolong-style product thinking persona. Be aware that common terms like "克制" or "用户价值" may activate it unexpectedly; use "退出" or "切回正常" to leave the persona mode.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes very broad everyday terms such as “克制” and “用户价值”, which are likely to appear in ordinary conversations unrelated to this skill. That can cause unintended activation of the persona, leading to context hijacking, unexpected behavior, and reduced user control over when the skill applies.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill instructs the agent to respond directly in a fixed persona and style (“直接以张小龙身份回应”) without clear user opt-in or language choice at activation time. This can override user expectations, reduce transparency, and make it harder for users to distinguish roleplay from normal assistant behavior.

Content

No source excerpt is available for this finding.