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
🌏 东南亚市场政策查询Skill
Security checks for vulnerabilities and agentic risk
Overview
This is a simple Chinese-language trade-policy lookup skill with no executable code, hidden install behavior, persistence, or credential handling.
Install only if you want Chinese-language assistance for Southeast Asia trade-policy research. Treat outputs as informational starting points and verify tariff, customs, and legal conclusions against current official sources before acting on them.
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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The invocation example '查关税政策' is very broad and overlaps with ordinary user requests about tariffs or trade policy. In agent environments that route based on natural-language matching, this can cause unintended skill activation, potentially sending user queries into this skill when they did not explicitly intend to use it.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 85% confidence
- Finding
The natural-language content presents the skill exclusively in Chinese and does not indicate that users may interact in other languages or opt into this locale. Under the policy, forcing a specific language without user choice can be a language/locale policy violation unless clearly justified as region-specific and documented as such.
- Content