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 即期本票
Security checks for vulnerabilities and agentic risk
Overview
This is a disclosed Chinese-language financial risk-reference skill with no executable code or persistence, but users should treat its banking and SBLC material as high-stakes informational guidance only.
Install only if you need Chinese-language reference material for promissory-note fraud review. Do not paste full ticket numbers, account data, SWIFT confirmations, customer names, authentication materials, or bank messages into the assistant unless they are approved and redacted. Treat the SBLC, tax, green-channel, and transaction-decision sections as non-binding background and verify any real transaction through your bank, counsel, and official regulators.
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
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- 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 (9)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 85% confidence
- Finding
The skill name and description, along with the rest of the document, assume Chinese as the mandatory operating language. Under the policy for natural-language violations, forcing a specific language without user opt-in can exclude users and is not justified here as a region-specific constraint.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The skill claims to be a promissory-note fraud-prevention guide, but it expands into broader financing and project workflows such as gold-project funding and related instrument handling. This scope drift can cause users to rely on the skill for higher-risk financial structuring guidance outside its declared purpose, weakening guardrails and increasing the chance of unsafe or noncompliant decisions.
- Content
Context-Inappropriate Capability
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
Including SBLC '回国机制', tax handling, and 'green channel' process guidance materially extends the skill into cross-border instrument movement and potentially sensitive regulatory workflows unrelated to basic promissory-note fraud prevention. Users could treat this as operational advice for moving financial instruments or navigating special approval paths without legal review, creating compliance, sanctions, or fraud-abuse risk.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The skill instructs users to perform bank/SWIFT verification and handle ticket numbers, bank confirmation messages, and related financial details, but it does not warn against sharing sensitive banking data in insecure channels or with the assistant. This can lead to unnecessary disclosure of confidential financial information, enabling privacy violations, social engineering, or downstream fraud.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
该模板全文以中文固定呈现，且未说明是否允许用户选择其他语言或是否仅面向特定中文工作场景。按照语言/地区政策要求，若技能默认强制单一语言而无用户选择或明确限定，属于自然语言层面的政策风险。
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The entire skill description and usage instructions are presented only in Chinese, with no indication that users may choose another language or that the skill is intentionally restricted to a Chinese-speaking or China-specific audience. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
This markdown file presents all guidance exclusively in Chinese, and there is no natural-language indication that users may choose another language or that the content is intentionally restricted to a Chinese-speaking audience. Under the language/locale policy check, forcing a specific language without user opt-in can be a policy violation.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 79% confidence
- Finding
该技能文件全文以中文撰写，并直接给出固定中文话术示例与操作说明，没有说明是否支持其他语言或允许用户按偏好选择输出语言。按照该规则，若技能在自然语言层面强制单一语言且无用户选择或明确、合理的区域限定，可能构成语言/locale 政策问题。
- Content