skills/ma1orek/replay/TanStack Start/Gen Agent Trust Hub

TanStack Start

Pass

Audited by Gen Agent Trust Hub on Sep 26, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of development dependencies from the NPM registry. This includes frameworks and tools such as @tanstack/react-start, @cloudflare/vite-plugin, and wrangler. These resources originate from well-known technology providers and Cloudflare, which is a trusted organization.
  • [COMMAND_EXECUTION]: Provides standard command-line instructions for project lifecycle management, including package installation (npm install), deployment (wrangler deploy), and file organization during framework migration (rm, mv). These operations are consistent with the documented purpose of setting up and upgrading a TanStack Start application.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents the handling of external data through server functions and loaders, which represents a standard surface for indirect prompt injection in web applications.
  • Ingestion points: Server functions (createServerFn) and route loaders (loader) defined in SKILL.md ingest data from request.formData() and request.context.cloudflare.env.
  • Boundary markers: The provided code snippets do not explicitly include boundary markers or delimiters for the ingested data.
  • Capability inventory: The skill uses the Bash, Read, Write, and Edit tools as defined in the allowed-tools metadata.
  • Sanitization: Standard sanitization or escaping logic for the ingested content is not explicitly provided in the boilerplate code, which is typical for framework-level documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 26, 2026, 11:46 AM