Security audit

China Visa Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a simple China visa guidance skill with no code execution, persistence, or hidden data movement, though users should avoid sharing unnecessary personal details.

Installers should treat this as general visa assistance, not official legal advice. Users should share only coarse location and trip details needed for guidance, and should not paste passport numbers, full financial records, application IDs, or other sensitive documents unless they intentionally choose to do so in the chat environment.

A.I.G

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

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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 (2)

Missing User Warnings

Medium

Confidence: 95% confidence
Finding: The skill asks for nationality, travel purpose, travel duration, prior visa history, and current location, which are sensitive personal/travel data points, but provides no privacy notice, minimization guidance, or handling limits. This creates avoidable privacy risk because users may disclose more personal information than necessary without understanding how it will be used or whether it should be shared at all.

Vague Triggers

Medium

Confidence: 89% confidence
Finding: The closing prompt, 'Ask me anything, anytime!', is overly broad and can cause the skill to engage on generic requests unrelated to China visas. In a multi-skill environment, that increases the chance of accidental triggering, context overreach, and collection of unnecessary user information beyond the intended scope.

Static analysis

No suspicious patterns detected.