increase-average-order-value
Pass
Audited by Gen Agent Trust Hub on Nov 16, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: Provides instructions for installing the Whop command-line interface through shell-piping commands, specifically 'curl -fsSL https://whop.com/install.sh | sh' and a PowerShell equivalent fetching from GitHub, which execute remote scripts.
- [DYNAMIC_EXECUTION]: Utilizes 'npx' to dynamically download and run the latest version of the '@whop/cli' package to perform configuration and deployment tasks.
- [EXTERNAL_DOWNLOADS]: References and fetches external resources for setup, including the 'agent-browser' skill from Vercel Labs' official repository and installation scripts from Whop's domain.
- [COMMAND_EXECUTION]: Instructs the agent to execute various shell commands for tool version checking, account authentication, and status monitoring using the Whop CLI.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted external data, such as commerce order exports and browser-inspected product pages, creating a vulnerability surface for indirect prompt injection.
- Ingestion points: 'references/offer-measurement.md' (processes order and entrant data exports) and 'references/offer-placement-and-configuration.md' (traces product and checkout routes using a browser).
- Boundary markers: The instructions do not define specific delimiters or include directives for the agent to ignore embedded instructions when processing external ecommerce data.
- Capability inventory: The skill can execute shell commands via CLI tools, perform automated browser sessions, and modify tool configurations.
- Sanitization: No explicit sanitization or validation requirements are established for the content of ingested commerce records or page-state data.
Audit Metadata