repetere/jsonx/jsonx-safety-review

Claude Code and agent skill by repetere/jsonx

Trust tier 2
  • community
LLM review pending
Source check pending

Checking that the SKILL.md file is still in the repository.

Install

npx vskill@latest install repetere/jsonx/jsonx-safety-review

SKILL.md

jsonx-safety-review

Use this skill when an agent is working with JSONX as dynamic interface output for generative UI.

Purpose

Help produce, validate, or review constrained JSONX/JXM payloads that can be rendered through a trusted host component registry. Do not generate arbitrary React source code unless the user explicitly asks for durable application code.

Safe output contract

  • Return valid JSON when asked for a payload.
  • Use only components approved by the host registry.
  • Use only documented props for each component.
  • Do not include JavaScript functions, inline event handlers, raw HTML, Markdown wrappers, unknown components, unknown props, or arbitrary CSS.
  • Use named action strings such as open_detail, draft_response, approve_item, reject_item, and filter_table instead of executable code.
  • Keep visible UI copy concise and business-focused.

Blocked JSONX features for generated output

Never use __dangerouslyEvalProps, __dangerouslyBindEvalProps, __dangerouslyEvalAllProps, __dangerouslyInsertFunctionComponents, __dangerouslyInsertClassComponents, __dangerouslyInsertComponents, __dangerouslyInsertReactComponents, __dangerouslyInsertJSONXComponents, __functionProps, or windowprops for untrusted model output.

Recommended workflow

  1. Confirm the allowed component registry and prop schema.
  2. Draft the JSONX payload as data, not code.
  3. Validate component names, props, children, and action names.
  4. Explain any validation assumptions to the user.
  5. Prefer fixture, paste, or bring-your-own-endpoint demos for browser-only sites.

Provider note

This skill is intentionally provider-neutral and is published in the JSONX repository for codex users.

Security

  • Security scanPassed, 90 of 100Pattern checks on the skill's files.
  • Model reviewNot runA model review is scheduled for the next rescan.

Quality evaluation

  • Task evaluationNot runNo evaluation yet. Run one in Skill Studio.

Source

Popularity

Repository stars
184
Repository forks
18
7-day trend score
26

Stars and forks are for the whole GitHub repository, not this skill alone. Not refreshed yet.

Works with

Any agent vskill installs to: 56 targets in all. These 39 have a page on this site.

  • Claude Code
  • Cursor
  • GitHub Copilot
  • Windsurf
  • Codex
  • Gemini CLI
  • Cline
  • Amp
  • Roo Code
  • Goose
  • Continue
  • Kilo Code
  • Junie
  • Trae
  • OpenHands
  • Qwen Code
  • AI Agent
  • Tabnine Chat
  • Sourcegraph Cody
  • Amazon Q
  • Firebase Genkit
  • Sweep
  • Devin
  • Phind
  • Mentat
  • Claude Desktop
  • Aider
  • GPT Pilot
  • Plandex
  • bolt.new
  • v0
  • Replit Agent
  • Anse
  • TypingMind
  • BetterChatGPT
  • LibreChat
  • Warp AI
  • Pieces
  • Fig AI
Embed badge
vskill VERIFIED badge
[![vskill VERIFIED](https://verified-skill.com/api/v1/skills/repetere/jsonx/jsonx-safety-review/badge)](https://verified-skill.com/skills/repetere/jsonx/jsonx-safety-review)

Something wrong with this skill or its page? Tell us.