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
Soilkworks自动化控制
Security checks for vulnerabilities and agentic risk
Overview
This skill coherently helps users generate SolidWorks automation scripts, with file creation and export behavior disclosed and tied to user-requested CAD tasks.
Before running generated SolidWorks automation, confirm the target model, dimensions, save/export paths, filenames, and overwrite behavior. Prefer testing on copies of important CAD 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
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The description advertises file saving and drawing export capabilities without warning users that these actions can overwrite files, create outputs, or otherwise modify user data. In a CAD automation context, omission of such warnings raises the risk of unsafe use, especially when generated code is intended to be run directly against a local SolidWorks installation.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The trigger words include broad phrases such as 'SolidWorks' and 'solidworks', which may cause the skill to activate in unintended contexts. Because this skill can generate automation code for CAD operations, accidental invocation increases the chance of unintended file creation, export, or modification workflows being suggested or initiated by users without clear intent.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The instruction requires that every key line of generated code include Chinese comments, which imposes a fixed language requirement. There is no indication that users can opt into another language or locale, making this a natural-language policy concern.
- Content