Tp2
High
- Category
- MCP Tool Poisoning
- Confidence
- 85% confidence
- Finding
Mixing characters from multiple Unicode scripts in a single identifier is a common technique to create visually ambiguous tool names.
- Content
Security audit
5WHY分析技能
Security checks for vulnerabilities and agentic risk
Overview
This is a Chinese 5 Whys root-cause-analysis guide made of markdown templates, with no executable code, external access, persistence, or credential handling.
Install this if you want a Chinese-language, structured 5 Whys facilitator. Be aware that it may take over generic root-cause requests and enforce a rigid format; it should not be treated as a substitute for expert judgment on safety-critical, engineering, or business decisions.
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
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The trigger conditions are broad enough to activate on generic requests about analyzing causes or solving problems, which can cause the skill to take over conversations outside its intended scope. In agentic environments, overbroad activation increases the risk of prompt/skill hijacking, inappropriate workflow selection, and disclosure of structured guidance in contexts where a different skill or safer default behavior should apply.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
This markdown file contains user-facing instructions and output templates exclusively in Chinese, which can amount to a language/locale policy violation when no user opt-in or alternative language option is provided. The document does not state that the skill is region-specific or limited to Chinese-speaking users.
- Content
Intent-Code Divergence
Low
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
L127-L136 的示例被标注为“中间原因判定”，但同时将“能彻底杜绝 → 判定为根本原因”和“若为根本原因 → 进入收尾阶段”也勾选为已满足。这与同一段中的“回答：会”“判定结论：中间原因”直接冲突，属于文档意图与内容表达不一致。
- Content
Static analysis
No suspicious patterns detected.