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
Excel Finance
Security checks for vulnerabilities and agentic risk
Overview
The skill is low-risk in what it runs, but it misleadingly claims to generate Excel finance files while the bundled code only prints canned messages.
Review this before installing because it appears to be a demo or placeholder rather than a working Excel automation skill. It does not show malicious behavior, but users expecting generated spreadsheets or real financial calculations should not rely on its success messages without verifying actual output files.
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 (5)
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
Tp4
High
- Category
- MCP Tool Poisoning
- Confidence
- 95% confidence
- Finding
声明的核心能力是 Excel 财务模型模板和自动化报表生成，这意味着代码应当实际创建 Excel 文件、填充表格、进行建模或报表输出。但该代码仅通过 print 输出固定文本和伪成功提示，虽然函数名和文案与财务建模相关，但没有使用任何 Excel 处理库、文件写入逻辑、数据源读取或计算流程。输出文件名仅作为字符串展示，并未真正生成文件。因此，代码的实际行为与声明用途存在实质性不符。
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The trigger phrases are broad finance terms that can match many ordinary user requests, causing the skill to activate outside narrowly intended scenarios. Over-broad activation increases the attack surface for prompt/skill routing mistakes and may cause untrusted skill instructions or external dependencies to be invoked when a general finance answer would have sufficed.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
This code file contains user-facing natural-language strings, comments, and docstrings exclusively in Chinese, including the script title and all printed output. Because the skill forces a specific language for user interaction without opt-in or justification, it presents a language/locale policy concern.
- Content
Static analysis
No suspicious patterns detected.