instacart-automation

Warn

Audited by Snyk on Jun 21, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

  • Potentially malicious external URL detected (high risk: 0.90). The skill requires adding and calling the remote MCP endpoint https://rube.app/mcp at runtime (via RUBE_SEARCH_TOOLS, RUBE_MANAGE_CONNECTIONS, RUBE_MULTI_EXECUTE_TOOL) to fetch tool schemas and recommended execution plans that directly control agent behavior and trigger remote tool execution, so this external URL is a runtime dependency that can control prompts/execute code.

MEDIUM W009: Direct money access capability detected (payment gateways, crypto, banking).

  • Direct money access detected (high risk: 1.00). The skill is a specialized Instacart toolkit integration (not a generic browser or HTTP tool). It requires an active "instacart" connection and instructs discovery and execution of toolkit tools via RUBE_MULTI_EXECUTE_TOOL — which, in the context of an Instacart toolkit, can include placing orders, performing checkout, and other commerce actions that result in payments. Although no specific payment gateway names (Stripe/PayPal/etc.) are listed, the skill is explicitly designed to automate a commercial ordering platform and therefore can directly execute financial transactions on behalf of a user. This meets the "specific tool for moving money" criterion rather than a generic capability.

Issues (2)

W012
MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

W009
MEDIUM

Direct money access capability detected (payment gateways, crypto, banking).

Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 21, 2026, 02:14 AM
Issues
2
Security Audit — snyk — instacart-automation