Security audit

chinacrive commercial claims ai

Security checks for vulnerabilities and agentic risk

Overview

This is a Chinese auto-insurance claims guidance skill with no executable code or hidden access, though users should handle listed identity, banking, and medical documents carefully.

Installers should treat this as informational claims guidance, not legal advice or an insurer’s official decision. Because it lists IDs, bank details, medical records, and other sensitive claim materials, users should avoid pasting full documents into chat and should submit them only through official, secure insurer channels when required.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (2)

Missing User Warnings

Medium

Confidence: 94% confidence
Finding: The document enumerates a broad set of highly sensitive personal, financial, and medical claim materials, including IDs, bank account information, medical records, and death-related documents, but provides no privacy, retention, access-control, masking, or secure-transmission guidance. In a claims-handling skill, this can normalize over-collection or unsafe handling of regulated personal information, increasing the risk of data leakage, misuse, or noncompliance when users or downstream agents follow the checklist literally.

Natural-Language Policy Violations

Low

Confidence: 89% confidence
Finding: The entire skill file is written only in Chinese and does not indicate that users may choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy concern.

Static analysis

No suspicious patterns detected.