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
ISO13485体系策划
Security checks for vulnerabilities and agentic risk
Overview
This is a Chinese-language ISO 13485 quality-system planning guide with templates and no executable behavior or hidden data access.
Install this as a documentation aid for Chinese-language ISO 13485 QMS planning. Users should verify generated compliance documents with qualified regulatory or quality professionals and clarify that requests are for medical-device ISO 13485 work when using broad terms like audit or certification preparation.
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
- 95% confidence
- Finding
The trigger conditions include broad phrases such as '建立QMS', '通过认证', and '准备审核', which can match a wide range of general quality, compliance, or audit requests beyond the narrowly intended ISO 13485 planning context. This can cause the skill to activate unexpectedly, leading to incorrect domain guidance, over-collection of user context, or workflow confusion in environments with multiple overlapping skills.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
This markdown file presents the audit guide exclusively in Chinese, beginning with the title and continuing throughout the document. 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 option or justification is provided.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 80% confidence
- Finding
This markdown file presents the skill content entirely in Chinese, including headings and instructional text, with no indication that the user can choose another language. Under the natural-language policy rule, forcing a specific language without user opt-in can be a policy concern.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
The title and all instructional content are written in Chinese, and the file does not indicate that language selection is optional or that the skill is specifically limited to a Chinese-speaking or region-specific context. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation.
- Content
Static analysis
No suspicious patterns detected.