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
Policy Japan Korea
Security checks for vulnerabilities and agentic risk
Overview
This is a disclosed policy-query skill for Japan and Korea trade compliance, with no code execution, credential access, persistence, or hidden data flow in the inspected artifacts.
Before installing, users should treat the skill as advisory and verify legal, customs, and certification answers against official Japanese and Korean authorities because the artifact itself notes that regulations change frequently. Users who prefer another language may need to ask for it explicitly because the skill text is primarily Chinese.
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
- 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
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill’s name, description, examples, and operating guidance are entirely presented in Chinese, and there is no statement that users may choose another language. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy violation unless the locale constraint is explicitly documented and justified.
- Content