setup-services
Fail
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the agent to download and immediately execute a script from
https://openspend.ai/installusingcurl | sh. This pattern is a critical security risk as it executes unverified remote code in the local shell environment. - [COMMAND_EXECUTION]: The skill performs multiple local shell operations, including package management via Homebrew (
brew install), Node.js package execution (npx), and direct CLI interactions for authentication and updates (openspend auth login). - [EXTERNAL_DOWNLOADS]: The skill fetches software and configurations from several external sources:
- Downloads an installer script from
openspend.ai. - Installs a Homebrew tap from the author's GitHub repository (
promptingcompany/tap/openspend). - Loads the
@coinbase/payments-mcppackage from the official NPM registry, which is a well-known payment service provider.
Recommendations
- HIGH: Downloads and executes remote code from: https://openspend.ai/install - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata