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
ISO14001环境管理体系策划
Security checks for vulnerabilities and agentic risk
Overview
This is a documentation-only ISO14001 planning skill whose data requests fit its stated purpose, with ordinary privacy and localization cautions.
Before installing, treat this as advisory planning support, not legal or certification advice. Provide only the organizational details necessary for customization, anonymize sensitive facility or process information where possible, and have final compliance documents reviewed by qualified personnel.
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
- 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
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 88% confidence
- Finding
The name, description, prompts, examples, and operating instructions are all in Chinese, which effectively fixes the interaction language. Under SQP-3, forcing a specific language without user opt-in can be a natural-language policy violation when no alternative or explicit locale justification is provided.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The skill explicitly collects potentially sensitive organizational information such as industry, scale, operating activities, pollution types, certification status, organization name, locations, and business processes without any privacy notice, minimization guidance, or handling restrictions. This can lead users to disclose operationally sensitive data that could be retained, shared, or misused, especially because environmental compliance and facility details may aid profiling or targeted social engineering.
- Content