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
🌍 非洲市场政策查询Skill
Security checks for vulnerabilities and agentic risk
Overview
This is a simple markdown-only skill for querying African trade policy, with no code, credentials, persistence, or hidden execution behavior found.
Review whether you want a Chinese-first skill and use specific prompts that mention Africa, the target country, product, or HS code. Treat its policy answers as reference only and verify important tariff, customs, or legal conclusions against official sources.
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 (3)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 84% confidence
- Finding
The skill is described entirely in Chinese and does not clearly offer language selection or opt-in, which can force interaction in a language the user did not choose. This is primarily a usability and policy-compliance issue, but it can also cause misunderstandings in regulatory or trade guidance where precise interpretation matters.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The trigger examples are very broad, such as generic requests to '查关税政策', which can overlap with normal user prompts and cause the skill to activate unexpectedly. Overbroad activation can lead to misrouting, unwanted context injection, or the skill answering outside its intended scope, which degrades safety and reliability even without explicit malicious behavior.
- Content