skills/keejkrej/based-skills/tooling/Gen Agent Trust Hub

tooling

Warn

Audited by Gen Agent Trust Hub on Jun 28, 2026

Risk Level: MEDIUMREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The documentation in scaffolds/ts-monorepo.md instructs the user to install the 'Vite+' (vp) toolchain using the command curl -fsSL https://vite.plus | bash. This pattern downloads and executes a script directly from a remote server, which can lead to full system compromise if the remote resource or the connection is malicious.
  • [EXTERNAL_DOWNLOADS]: The skill requires downloading tools and connecting to external domains including https://vite.plus, https://agent-browser.dev (for an MCP server), and several npm packages.
  • [COMMAND_EXECUTION]: The skill makes extensive use of npx to execute third-party CLI tools (e.g., agent-browser, ctx7, shadcn, create-astro, create-turbo) directly from the npm registry. This dynamically fetches and executes code at runtime without explicit local version pinning in some cases.
  • [COMMAND_EXECUTION]: The skill instructions in SKILL.md and domains/dev.md promote the use of npx @playwright/cli eval to execute arbitrary JavaScript code within a browser environment for reconnaissance and interaction with web pages.
  • [COMMAND_EXECUTION]: The skill utilizes uv run and uv add to manage and execute Python-based tools like pymobiledevice3 and ty, involving package installation and execution of external scripts.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Jun 28, 2026, 07:47 PM
Security Audit — agent-trust-hub — tooling