web-artifacts-builder

Pass

Audited by Gen Agent Trust Hub on Mar 9, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell scripts (scripts/init-artifact.sh and scripts/bundle-artifact.sh) to automate project setup, configuration, and the build pipeline. This includes extracting a component library using tar, modifying files with sed, and executing inline JavaScript via node -e for programmatic configuration updates.\n- [EXTERNAL_DOWNLOADS]: The initialization and bundling processes download and install over 50 dependencies from the NPM registry, which is a well-known and trusted service. This includes the Vite build tool, Tailwind CSS, and various UI component libraries.\n- [PROMPT_INJECTION]: The skill creates a development surface that is potentially vulnerable to indirect prompt injection, as it involves the agent generating and processing code based on user-provided requirements.\n
  • Ingestion points: User instructions for artifact development and source file edits.\n
  • Boundary markers: Absent.\n
  • Capability inventory: High-privilege capabilities including shell execution, package installation, and file system write access.\n
  • Sanitization: No sanitization or validation of the generated code is performed during the bundling process.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 9, 2026, 01:51 PM