web-artifacts-builder

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The initialization and bundling scripts install various standard development packages from the public NPM registry. Key packages include Vite, Tailwind CSS, Parcel, and Radix UI components (scripts/init-artifact.sh, scripts/bundle-artifact.sh).
  • [COMMAND_EXECUTION]: The initialization script (scripts/init-artifact.sh) installs the pnpm package manager globally using npm install -g if the command is not found.
  • [PROMPT_INJECTION]: The skill facilitates the creation of web-based artifacts that may process untrusted data at runtime.
  • Ingestion points: The generated React application is intended to render content within an AI agent's artifact view (SKILL.md).
  • Boundary markers: The scripts do not automatically include delimiters or specific instructions to ignore embedded prompts in the generated boilerplate.
  • Capability inventory: The skill uses shell scripts to perform file system operations, install packages, and execute build tools (scripts/init-artifact.sh, scripts/bundle-artifact.sh).
  • Sanitization: No explicit content sanitization or validation logic is implemented in the project setup scripts.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 12:34 PM
Security Audit — agent-trust-hub — web-artifacts-builder