ClawHub
Back to skill

Security audit

China Insurance Advisor

Security checks across malware telemetry and agentic risk

Overview

This skill is a clearly disclosed proxy that sends insurance questions to a third-party chat service, with privacy-sensitive use that users should understand before installing.

Install only if you are comfortable sending insurance-related messages to whylingxi.cn. Avoid sharing unnecessary medical, financial, identity, or family details, and use reset-session or clear the session mapping file when you do not want continued conversation linkage.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (5)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill is documented as executing a Python script that performs outbound network requests, persists multi-turn state via session_id, and likely reads integration details from local files, yet it declares no permissions. This creates a capability-transparency gap that can bypass platform review and user/admin expectations about data access and external transmission.

Missing User Warnings

Medium
Confidence
98% confidence
Finding
The skill forwards user insurance questions to a third-party remote chat service without an explicit user-facing notice that their content will leave the local system. Insurance discussions routinely contain sensitive personal and financial information, so silent transmission materially increases privacy, compliance, and data-handling risk.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The notes explicitly describe forwarding user messages to a remote third-party chat service and persisting a local mapping of session identifiers, but provide no warning about data handling, retention, or user consent. In an insurance-advice context, users may submit sensitive personal and financial information, so undocumented remote transmission and local session persistence creates a real privacy and confidentiality risk.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The skill forwards arbitrary user messages to a third-party remote service (`https://whylingxi.cn/chat`) and persists conversation linkage via `session_id`, but the code shows no disclosure, consent, minimization, or safeguards for sensitive data. In this skill context, users are likely to share highly sensitive financial, health, family, and insurance information, so undisclosed transmission to an external endpoint creates a meaningful privacy and compliance risk.

Direct Prompt Extraction

High
Category
System Prompt Leakage
Content
Use `--reset-session` to start a fresh upstream conversation.

## Output rules

- Prefer direct passthrough
- Do not summarize unless the user asks
Confidence
92% confidence
Finding
Output rules

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.