Razorpay

Security checks across malware telemetry and agentic risk

Overview

This appears to be a legitimate Razorpay integration, but it can give an agent broad live payment-account control without clear confirmation or safety boundaries.

Install only if you trust Membrane and intend to let an agent work with Razorpay. Prefer a sandbox or least-privileged Razorpay connection, explicitly approve every write, refund, payment-link, fund-account, or delete action, and revoke the Membrane/Razorpay connection when finished.

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: 90% confidence
Finding: The skill explicitly documents a generic proxy mechanism that supports POST, PUT, PATCH, and DELETE against the Razorpay API without any guardrails, confirmation requirements, or warning that these methods can create, modify, or delete live payment-platform data. In a payments context, exposing raw mutating requests increases the risk of accidental destructive actions or unsafe agent-generated calls, especially when the proxy is presented as a fallback for unsupported use cases.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal