Toast

Security checks across malware telemetry and agentic risk

Overview

This Toast skill appears purpose-aligned, but it gives an agent broad authenticated access to restaurant POS data and raw write/delete API capability without clear confirmation safeguards.

Install only if you are comfortable letting an agent operate through a Membrane-connected Toast account. Use the least-privileged Toast access available, prefer prebuilt/read-only actions, require manual confirmation before any create/update/delete or order/customer/payment-adjacent change, and revoke the Membrane 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: 91% confidence
Finding: The skill explicitly documents raw proxy requests with support for POST, PUT, PATCH, and DELETE without requiring confirmation, approval gates, or warnings about modifying production restaurant data. In a POS context, direct mutation can affect orders, customers, or operational records, increasing the risk of accidental or unauthorized destructive actions.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal