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
胡田 OPC导师 黄金交易
Security checks for vulnerabilities and agentic risk
Overview
This is a Chinese-language reference skill for cross-border gold-trading compliance and fraud checks, with no executable code or hidden agent-control behavior found.
Treat this as a checklist and drafting aid, not as legal, tax, banking, or investment advice. Verify current regulations, tax rates, bank details, SWIFT messages, and counterparties through qualified professionals and official channels before acting, and avoid entering real account or transaction details into platforms you do not trust.
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 (7)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 81% confidence
- Finding
The skill name and description are entirely in Chinese and the document provides no indication that users may interact in other languages or choose a preferred locale. Under the policy rule, language constraints should be opt-in or explicitly justified as region-specific; here the content is region-focused on cross-border gold trade, but it does not clearly state that Chinese-only use is intentional or required.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 77% confidence
- Finding
文件全文以中文撰写，并将适用范围表述为“适用于老挝/东南亚金矿采购”，但未说明是否支持其他语言或是否允许用户选择语言/区域设置。按规则，若技能在自然语言层面隐含固定语言/地区而无用户选择或明确合理说明，可能构成语言/locale 策略问题。
- Content
Vague Triggers
Low
- Category
- Not specified by scanner
- Confidence
- 85% confidence
- Finding
这是一个 markdown 文件，适用 SQP-1。README 仅说明“导入 SKILL.md 文件”“根据需要配置相关参数”“开始使用”，但没有给出明确的触发短语、适用场景边界或排除条件，容易导致技能被过宽泛地理解为适用于任意黄金交易咨询场景。
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This markdown file presents all instructions, checklist items, and warnings exclusively in Chinese. Under the policy rule for natural-language violations, forcing a specific language without user opt-in can be a locale-policy issue when no alternative language choice or justification is provided.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
该手册全文以中文呈现，且未说明这是面向特定中文用户群体的区域性合规文档，也未提供其他语言或用户选择。根据规则，若技能内容默认强制单一语言且没有用户 opt-in，属于可报告的自然语言政策问题。
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 82% confidence
- Finding
该技能全文使用中文提供操作指引，但文档中没有说明这是面向中文用户的区域性资料，也没有提供其他语言选项或用户可选择语言的提示。按规则，若技能强制特定语言且无用户选择或明确合理说明，可视为自然语言层面的语言/locale政策问题。
- Content