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
胡田 OPC导师 培训体系
Security checks for vulnerabilities and agentic risk
Overview
This is a Chinese-language OPC mentor training content skill with disclosed document outputs and no evidence of hidden execution, credential access, exfiltration, or persistence.
Install this if you want a Chinese-language OPC mentor training framework. Before using file-generation features, confirm the agent will write only the listed Markdown files under ./output/ and will not overwrite existing work without approval.
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 (4)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill description is broad and lacks explicit scope boundaries, exclusions, or safety conditions, which can cause the agent to apply the skill in contexts the author did not intend. In agent systems, overly broad triggering increases the chance of inappropriate file generation, misuse in adjacent workflows, or accidental invocation where sensitive or destructive actions may follow.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 90% confidence
- Finding
The skill documentation is entirely written in Chinese, including the title, description, pricing, and usage instructions, with no indication that users may choose another language or that the skill is intended only for a Chinese-speaking or region-specific audience. This can conflict with language/locale policy expectations when users are not given an explicit opt-in or alternative.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The document instructs the generation of output files under './output/' without clearly requiring user awareness or confirmation before write actions occur. Even though the files appear benign, silent file creation is risky in agent environments because it can overwrite existing work, create misleading artifacts, or normalize unconsented side effects.
- Content
Static analysis
No suspicious patterns detected.