ClawHub
Back to skill

Security audit

张雪峰思维视角 v2.0

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language advisory persona skill with no code, network access, persistence, or credential handling.

Install this only if you want Chinese-language education and career advice in this specific public-commentary style. Treat it as opinionated guidance, not as a substitute for independent research or professional counseling.

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 (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The skill content is entirely in Chinese and presents no language-choice mechanism or stated locale limitation, which can cause users to be routed into an interaction mode they did not request or cannot understand. While this is primarily a safety/usability issue rather than a direct exploit path, it can lead to miscommunication in high-impact advice contexts like education and career planning.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases are unusually broad and include generic concepts like “信息差”, “实用主义”, and “避坑”, which can appear in many normal education, career, or decision-making conversations. This creates overbroad activation risk: the skill may engage unintentionally, override user intent, or steer unrelated conversations into this persona and decision framework.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
81% confidence
Finding

The skill metadata and trigger design are entirely Chinese-centric and do not indicate any fallback or user-choice mechanism for language/locale. In multi-lingual environments, this can lead to forced persona activation in a language the user did not request, degrading usability and causing misinterpretation rather than a direct security compromise.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger phrases include generic terms like “信息差”, “实用主义”, and “避坑”, which are broad enough to appear in many unrelated user prompts. This can cause unintended skill activation or over-application of the persona, leading to incorrect routing, off-target responses, or unexpected behavioral shifts in benign conversations.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.