Skills
skills/zhanlincui/ultimate-agent-skills-collection/web-artifacts-builder/Gen Agent Trust Hub

web-artifacts-builder

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (HIGH): The script scripts/init-artifact.sh attempts to install a global package using npm install -g pnpm. Global installations typically require administrative (root) privileges, posing a risk of privilege escalation.
  • COMMAND_EXECUTION (MEDIUM): The script scripts/init-artifact.sh utilizes node -e to execute dynamically constructed JavaScript code for modifying project configuration files (tsconfig.json and tsconfig.app.json).
  • EXTERNAL_DOWNLOADS (LOW): The scripts scripts/init-artifact.sh and scripts/bundle-artifact.sh automatically install a large number of Node.js dependencies from the npm registry at runtime, including parcel, vite, and numerous UI components.
  • PROMPT_INJECTION (LOW): The skill initialization script accepts a project name as a command-line argument which is used directly in shell commands and file writing without sanitization, creating a surface for indirect prompt injection. (Evidence: Ingestion point in init-artifact.sh via $1; Boundary markers: Absent; Capability: Shell execution and file creation; Sanitization: Absent).
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 06:24 PM