ClawHub

Lightningprox

Security checks across malware telemetry and agentic risk

Overview

This skill is a disclosed guide for using a paid LightningProx AI gateway, but prompts and a prepaid spend token are sent to LightningProx when used.

Install only if you intend to let the agent make paid AI requests through LightningProx. Use a limited-balance spend token, avoid sending secrets or regulated data in prompts unless you approve the service for that use, and review the optional npm SDK separately before adding it to a project.

SkillSpector

By NVIDIA
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
87% confidence
Finding
The skill explicitly instructs users to send prompts and an authentication token to a third-party endpoint, but it does not provide a clear warning that prompts, model inputs, and billing/auth data leave the local environment and may be retained in request logs. The later trust statement even says 'No data stored beyond request logs,' which confirms logging but still does not present a prominent privacy warning near the usage examples.

External Transmission

Medium
Category
Data Exfiltration
Content
```bash
# 1. Top up at lightningprox.com/topup — pay Lightning invoice, get token
# 2. Use token directly
curl -X POST https://lightningprox.com/v1/messages \
  -H "Content-Type: application/json" \
  -H "X-Spend-Token: $LIGHTNINGPROX_SPEND_TOKEN" \
  -d '{
Confidence
90% confidence
Finding
curl -X POST https://lightningprox.com/v1/messages \ -H "Content-Type: application/json" \ -H "X-Spend-Token: $LIGHTNINGPROX_SPEND_TOKEN" \ -d '{ "model": "claude-sonnet-4-6", "messages"

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal