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
8D报告技能
Security checks for vulnerabilities and agentic risk
Overview
This skill is a coherent Chinese 8D quality-report assistant that collects report details and can optionally export a local Word file after user confirmation.
Install only if you want a Chinese-language 8D reporting workflow. Review any names, phone numbers, emails, customer details, and quality data before exporting a Word file, and omit or redact fields your organization should not store in reports.
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)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The trigger conditions are broad ('生成8D报告', '编写质量问题分析报告' etc.), which can overlap with ordinary conversation and cause the skill to activate unexpectedly. Because the skill then begins structured collection of business and personal data, accidental invocation can lead to unnecessary data disclosure or confusing workflow hijacking.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill collects and outputs personal contact information such as names, phone numbers, and email addresses in the generated report, but the description does not clearly warn users about this data handling. In a quality-reporting context this increases privacy and compliance risk, especially if users provide third-party staff details without noticing they will be stored, displayed, and potentially exported to Word.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
标题“8D方法论与评分标准”以及全文内容均以中文编写，且未说明这是仅适用于中文用户或特定区域的材料，也没有提供多语言选项。根据规则，强制特定语言而无用户选择属于自然语言层面的语言/locale policy violation。
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
This markdown file contains user-facing dialogue guidance exclusively in Chinese from the title onward, with no indication that other languages are supported or that Chinese is an optional locale. Under the policy rule, forcing a specific language without user opt-in is a natural-language policy concern.
- Content
Static analysis
No suspicious patterns detected.