Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 70% confidence
- Finding
Without declared permissions the skill's intent is opaque and cannot be validated.
- Content
Security audit
旅行插头电压查询
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local Chinese-language travel plug and voltage lookup tool with no evidence of network access, persistence, destructive behavior, or data exfiltration.
Install this if you want Chinese-language, offline travel plug and voltage guidance. Be aware that it relies on embedded reference data, so verify critical electrical compatibility against device labels or hotel/local guidance before using high-power appliances; the unused PROXY_TOKEN read is unnecessary but showed no data flow or security impact in the inspected code.
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 Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- 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 (3)
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The skill description and all user-facing output strings are presented in Chinese, which effectively forces a specific language for users. The file does not indicate that Chinese is optional, user-selected, or justified as a region-specific constraint.
- Content
Natural-Language Policy Violations
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
Multiple returned messages, errors, and guidance strings are hardcoded in Chinese across the executable functions. Because the skill provides no mechanism for language selection or explicit regional scoping, this violates the language/locale choice policy.
- Content