Stripe Treasury

Security checks across malware telemetry and agentic risk

Overview

This Stripe skill is broadly aligned with managing Stripe accounts, but it gives agents an under-scoped way to make authenticated Stripe API calls that could modify financial or business data.

Install only if you trust Membrane and are comfortable connecting a Stripe account. Use the narrowest Stripe permissions possible, prefer the listed Membrane actions over raw proxy requests, and require explicit approval before any create, update, delete, payout, transfer, refund, subscription, or balance-affecting operation.

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: 91% confidence
Finding: The skill explicitly provides a generic proxy request mechanism capable of sending arbitrary authenticated requests to Stripe Treasury endpoints, including state-changing methods like POST, PUT, PATCH, and DELETE, without requiring confirmation or warning about financial or data-modification consequences. In a banking/treasury context, this materially increases the risk of unauthorized transfers, payout changes, or sensitive financial data access if the agent follows these instructions too broadly.

VirusTotal

64/64 vendors flagged this skill as clean.

View on VirusTotal