ClawHub

Invoice Verification - 发票查验

Security checks across malware telemetry and agentic risk

Overview

This skill transparently verifies invoices through JisuAPI, but users should know invoice details are sent to that third party.

Install only if you are authorized to share the relevant invoice information with JisuAPI. Use a dedicated API key, watch quota or billing, and confirm before submitting invoices that contain personal, tax, or sensitive business details.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
82% confidence
Finding
The activation guidance uses broad natural-language triggers such as '帮我验一下这张增值税发票' and '这张票能不能报销查验', which could cause the skill to activate on loosely related requests. Because the skill sends sensitive invoice details to a third-party verification service, overbroad activation increases the chance of unintended data disclosure or unexpected external calls.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The documentation instructs users or agents to transmit detailed invoice information, including invoice codes, numbers, dates, amounts, and possibly tax identifiers, to a third-party API without a clear privacy notice or consent step. These records can contain personal or commercial sensitive data, so silent external transmission creates privacy and compliance risk.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill transmits user-supplied invoice data, which can include sensitive financial and tax identifiers, to `api.jisuapi.com` without any visible consent flow, disclosure, or minimization controls. In this skill context, external transmission is expected for verification, but the lack of explicit user-facing notice and privacy guardrails makes the data-sharing risk real.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal