ClawHub
Back to skill

Security audit

emperor-sui-wendi

Security checks for vulnerabilities and agentic risk

Overview

This is a markdown-only Chinese roleplay strategy-advice skill with no code execution, persistence, credential access, or hidden data handling.

Install this if you want Chinese-language, persona-driven strategic advice. Treat its decisive recommendations as framing, not as a substitute for professional financial, legal, medical, or business judgment.

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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The trigger condition is extremely broad: it activates for nearly any strategic, management, investment, or decision-making question. This can cause accidental invocation in ordinary conversations, leading the model to adopt a strong persona and prescriptive decision style when the user did not explicitly request it, which may distort advice or override normal assistant behavior.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

文件标题、描述及主体指令均固定为中文表达，且未说明是否可根据用户偏好切换语言或地区表达方式。根据规则，若技能强制特定语言而未提供用户选择，可能构成自然语言层面的语言/locale 政策问题。

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.