ClawHub
Back to skill

Security audit

Aiprox Swarm

Security checks across malware telemetry and agentic risk

Overview

The skill appears to be a disclosed market-question helper that sends user-provided prompts to a third-party service, with documentation clarity issues but no evidence of hidden, destructive, or unrelated behavior.

This looks acceptable to install if you are comfortable using a third-party market-analysis service. Treat everything you type into it as data sent outside your machine, avoid confidential or regulated information, and confirm the spend-token/authentication model before relying on it for billing or access control.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Intent-Code Divergence

Medium
Confidence
98% confidence
Finding
The skill makes contradictory security claims: the examples require an `X-Spend-Token`, but the trust statement says no authentication or API key is required. This can mislead users about access control and billing/security expectations, causing them to disclose data or invoke the service under false assumptions.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill explicitly instructs users to send free-form questions and optional contextual news to a third-party service, but it does not clearly warn that this content leaves the local environment and is processed by `aiprox.dev`. Because context may include proprietary trading ideas, unreleased research, or sensitive market information, users may unintentionally disclose confidential data.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.