Security audit

中文多智能体辩论

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese-language debate-simulation skill with no code execution, persistence, credential access, or hidden data handling observed.

Install this if you want debate requests handled as structured Chinese Oxford Union-style simulations. Be aware that it may steer broad argument-testing requests into a multi-round debate format and may use multiple model-role generations, but no local data, credentials, persistence, or privileged actions were evident.

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 (3)

Natural-Language Policy Violations

Medium

Confidence: 96% confidence
Finding: L003 明确将技能描述为“中文多辩手辩论”，这本身设定了语言限制；随后全文提示词也一致要求扮演“中文辩手”。该文件没有说明这是可选语言模式，也没有给用户提供语言/locale 选择，因此构成强制特定语言的自然语言策略问题。

Vague Triggers

Medium

Confidence: 83% confidence
Finding: L009 说明当用户想要“辩论”“检验论证强度”“准备正式辩论”时触发，其中“检验论证强度”等表述范围较广，可能覆盖普通分析、写作辅助或观点比较等常见请求。该处未列出明确触发短语、限定上下文或负面示例，容易导致意外调用。

Natural-Language Policy Violations

Medium

Confidence: 92% confidence
Finding: L043 的系统提示直接规定“你是一名经验丰富的中文辩手”，后续反方与流程也延续这一约束。对于通用辩论技能，这会在未征得用户同意的情况下强制语言/locale，属于应避免的自然语言策略违例。

Static analysis

No suspicious patterns detected.