artifacts-builder

Pass

Audited by Gen Agent Trust Hub on Aug 6, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell scripts to automate project setup and bundling tasks.
  • Evidence: Execution of npm, pnpm, tar, sed, and node -e within scripts/init-artifact.sh and scripts/bundle-artifact.sh to initialize project structures and generate configuration files.
  • [EXTERNAL_DOWNLOADS]: The skill downloads numerous dependencies from the official npm registry during the initialization and bundling processes.
  • Evidence: Use of npm install -g pnpm, pnpm create vite, and various pnpm install commands for frontend libraries and build tools.
  • [PROMPT_INJECTION]: The skill exposes an attack surface for indirect prompt injection by accepting a user-supplied project name that is used in shell commands and file system operations.
  • Ingestion points: The <project-name> argument in scripts/init-artifact.sh.
  • Boundary markers: None present.
  • Capability inventory: The skill can create directories, write configuration files, and execute shell commands based on the project name.
  • Sanitization: No explicit validation or sanitization is performed on the input string, though the risks are mitigated by the development-oriented context.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 6, 2026, 04:52 PM
Security Audit — agent-trust-hub — artifacts-builder