ClawHub
Back to skill

Security audit

aremes-catalog

Security checks across malware telemetry and agentic risk

Overview

The skill is transparent about being an art-commerce catalog, but it enables buyer-data submission, order creation, and payment workflows without clear approval safeguards.

Review before installing if you do not want an agent interacting with merchant checkout APIs. Treat browsing and quote lookup as lower risk, but require explicit approval before creating purchase intents, sending buyer contact details, verifying orders, or initiating any Stripe or USDC payment.

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 (1)

Missing User Warnings

Medium
Confidence
88% confidence
Finding
The skill instructs agents to collect and transmit buyer_email, and optionally buyer_name, buyer_org, and message, to third-party commerce endpoints without any explicit notice, consent guidance, minimization rules, or link to a privacy policy. This creates a real privacy and compliance risk because an agent may send personal data to external services by default, and the endpoints are public and unauthenticated, increasing the chance of inappropriate disclosure or misuse.

VirusTotal

66/66 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.