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
A Stocks Analysis
Security checks for vulnerabilities and agentic risk
Overview
This is a read-only stock market data skill with disclosed API-key use and no executable install or persistence behavior.
Before installing, confirm you are comfortable configuring TAX_API_KEY for the tax.yyyou.top stock data service. Treat outputs as research only, and ask the agent to clarify when a request is about a generic announcement or policy topic rather than a specific stock, issuer, exchange, or market context.
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)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 89% confidence
- Finding
The trigger list includes very broad, everyday terms such as '公告' and '政策法规', which can match many non-stock user requests and cause this skill to capture prompts outside its intended scope. In a multi-skill environment, overbroad routing can lead to unintended data access patterns, user confusion, or bypass of more appropriate skills and clarifications.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 83% confidence
- Finding
文件标题和全文内容均以中文面向使用者编写，但没有说明该技能仅限中文用户，亦未提供语言/locale 选择。这会构成自然语言层面的语言策略约束，因为技能实际上默认并强制单一语言而缺少用户 opt-in。
- Content
Static analysis
No suspicious patterns detected.