checkout-debug
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides instructions for the automated installation of the Whop CLI using remote scripts piped to the shell (curl | sh) and PowerShell (irm | iex). These installation commands target the official platform domains for Whop, which is a well-known service in the commerce ecosystem.
- [EXTERNAL_DOWNLOADS]: Fetches documentation, CLI tools, and configuration files from external sources, including official platform repositories and the vendor's own GitHub organization.
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external storefront data, cart states, and checkout flows, which exposes the agent to untrusted data that could contain indirect prompt injection instructions.
- Ingestion points: External ecommerce checkout pages and commerce records accessed via browser reproduction (references/browser-reproduction.md).
- Boundary markers: Includes instructions to keep customer data minimal and local, and to respect existing user sessions.
- Capability inventory: Includes the ability to execute CLI commands and perform network operations via browser tools.
- Sanitization: No explicit sanitization or filtering of external content is defined within the instructions.
- [COMMAND_EXECUTION]: Utilizes npm and npx for installing and executing the @whop/cli package to manage platform integrations.
Audit Metadata