tapcart-project
Pass
Audited by Gen Agent Trust Hub on Oct 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple shell commands to manage the development lifecycle, including
npm install,npm init, and varioustapcartCLI subcommands such asauth,block,dependency,lint,log, andlayout. These are standard operations for a developer tool. - [EXTERNAL_DOWNLOADS]: The skill downloads and installs official vendor packages from the npm registry, specifically
@tapcart/tapcart-cliand@tapcart/tapcart-app. These are legitimate tools provided by the author for the intended project management tasks. - [INDIRECT_PROMPT_INJECTION]: The skill accepts user-supplied input (App ID and folder name) and interpolates them into shell commands during project initialization. While this creates an attack surface, the risk is minimal given the developer-focused use case.
- Ingestion points: User input for
<app-id>and<folder-name>in thenpm initstep. - Boundary markers: No specific boundary markers are defined in the instructions to delimit user input from the shell command structure.
- Capability inventory: The skill possesses command execution capabilities through the global CLI and npm package manager.
- Sanitization: No explicit sanitization or escaping of the user-provided strings is described in the skill instructions.
Audit Metadata