web-artifacts-builder

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill implements a standard frontend build environment. The operations performed, such as initializing a project structure, configuring build tools (Vite, Parcel), and managing dependencies, are well-aligned with the stated purpose of building web artifacts.
  • [COMMAND_EXECUTION]: The automation scripts (scripts/init-artifact.sh and scripts/bundle-artifact.sh) execute shell commands to manage the development lifecycle. These include using pnpm for package management, node for configuration manipulation, and tar for local file extraction. All command patterns are transparent and standard for build automation.
  • [EXTERNAL_DOWNLOADS]: The skill installs numerous frontend libraries from the official NPM registry. These packages include established frameworks and utilities such as React, Vite, Tailwind CSS, and Radix UI components. The use of version-specific installations (e.g., tailwindcss@3.4.1) follows security best practices for reproducible builds.
  • [INDIRECT_PROMPT_INJECTION]: The skill functions as a code-generation helper. While it ingests and processes code generated by the agent based on user input, the risk of malicious code injection is mitigated by the intended use case of creating sandboxed web artifacts. The scripts themselves do not execute the generated artifact code in a privileged context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 07:46 PM
Security Audit — agent-trust-hub — web-artifacts-builder