ClawHub
Back to skill

Security audit

AI Debate Coach - 吵架助手

Security checks for vulnerabilities and agentic risk

Overview

This is a simple Chinese-language debate coaching prompt with no code, persistence, credential access, or hidden execution behavior.

Install only if you want a Chinese debate/rebuttal assistant. Review outputs carefully in sensitive personal conflicts, and avoid using the stronger phrasing to harass, threaten, or escalate disputes.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Natural-Language Policy Violations

Medium
Confidence
96% confidence
Finding
The skill description and content are written to operate in Chinese without any opt-in or language negotiation. This can override user language preferences, reduce transparency for non-Chinese users reviewing the skill, and increase the chance of misunderstanding or unsafe outputs if the user expects another language.

Vague Triggers

Medium
Confidence
94% confidence
Finding
The skill activates on a very broad condition: whenever a user wants to rebut someone, analyze arguments, or organize language. This can cause over-triggering in adjacent contexts such as interpersonal conflict, harassment, or emotionally escalated exchanges, leading the agent to produce adversarial coaching when the user did not explicitly request this specialized behavior.

Static analysis

No suspicious patterns detected.