skybridge

Skill · GitHub · ★ 2.2k · graded 2026-10-21Source linked

Skybridge is a full-stack TypeScript framework for MCP Apps and ChatGPT Apps. Type-safe. React-powered. Platform-agnostic.

No outside reports on file

Skybridge lets AI systems run your code, so you must carefully control what permissions, API keys, and data you give to any skill you build with it.

Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee.

Was this verdict for Skybridge helpful?

What it can access

Local filesNo local folder access notedLOW
Command executionNo shell command runner notedLOW
Network reachConnects to outside service APINOTED
CredentialsRequires API key or tokenREVIEW
Package sourceGitHub (alpic-ai/skybridge)PUBLIC

Inferred from this listing’s public package details and description. Check the project’s source before installing.

Install

No npm or PyPI package is listed. Install from source: github.com/alpic-ai/skybridge ↗

All setup options ↓

Check this skill Watch it in my stack Compare README badge View project

Everything known

We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.

0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30

Popularity grade: C (from public signals such as stars and downloads, not a code review). Graded 2026-10-21.

Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.

Check a specific version →

About Skybridge

Skybridge is a framework for building AI agent skills using TypeScript. It helps developers create tools that work with ChatGPT and other AI systems that use the MCP (Model Context Protocol) standard.

Who it’s for

TypeScript developers building AI agent applications or integrations. Teams who want type-safe code and React components for their AI tools.

Alternatives

Anthropic's Model Context Protocol (MCP): The standard that Skybridge implements
OpenAI's custom GPT actions: Native way to add tools to ChatGPT
LangChain tools: Python framework for building AI agent integrations
Viem or ethers.js: If building blockchain-specific agent skills

Setup

Check these steps against the project’s own instructions before running anything.

Follow the project's README. The GitHub repository at https://github.com/alpic-ai/skybridge (opens external site) contains setup instructions and examples.

Why this grade

CC — Moderate risk signals

Signal-based grade (3/7 points): well starred on GitHub, public source code. This reflects adoption and transparency, not a code review.

Popularity and upkeep

36/100

GitHub stars: 2.2k
Listing last refreshed: 2026-10-29

These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.

Risks to watch for

Unverified code execution: The framework runs TypeScript code that AI systems request, so malicious prompts could trigger unintended actions
Access to connected services: Skills built with Skybridge can access any API keys or credentials provided to them
Data passed through AI systems: Information sent to ChatGPT or other platforms may be logged or used for model training
Prompt injection attacks: AI systems using these skills could be tricked into calling functions with harmful parameters
Dependency vulnerabilities: TypeScript packages and libraries used by Skybridge could contain security flaws

How to lower the risk

Least-privilege permissions

Only provide API keys for services the skill actually needs
Use read-only credentials when possible

Network isolation

Run skills in separate environments from production systems
Restrict outbound network access to required endpoints only

Monitoring

Log all function calls made by AI systems
Alert on unusual or repeated failed requests

Red flags to watch for

Unexpected network requests or data exfiltration
AI systems requesting actions outside their normal scope

Questions

How do I install Skybridge?

Skybridge does not publish a standalone npm or PyPI package. Clone or follow the setup instructions in its source repository at github.com/alpic-ai/skybridge.

Are there security reports about Skybridge?

No reports found for this package in our research (last checked 2026-10-30). Skybridge currently holds Grade C (Moderate risk signals) based on public adoption and transparency signals. Key risk areas to watch include unverified code execution, access to connected services, data passed through ai systems.

Is Skybridge actively maintained?

Skybridge has 2.2k GitHub stars. Our directory data was last refreshed on 2026-10-29. Check recent commit activity, release tags, and open issues at github.com/alpic-ai/skybridge before pinning it in production.

What are alternatives to Skybridge?

Notable alternatives to Skybridge include Anthropic's Model Context Protocol (MCP) (The standard that Skybridge implements), OpenAI's custom GPT actions (Native way to add tools to ChatGPT), LangChain tools (Python framework for building AI agent integrations), Viem or ethers.js (If building blockchain-specific agent skills). You can also compare Skybridge side by side with other skills in the Related tools section on this page.

Maintain or use Skybridge? Show its live grade in your GitHub README, docs site, or run a check from the terminal before you install.

GitHub README Markdown:

markdown

[![AgentArmorHQ Risk Grade for Skybridge](https://agentarmorhq.com/api/badge/alpic-ai-skybridge)](https://agentarmorhq.com/skills/alpic-ai-skybridge)

HTML embed:

html

<a href="https://agentarmorhq.com/skills/alpic-ai-skybridge"><img src="https://agentarmorhq.com/api/badge/alpic-ai-skybridge" alt="AgentArmorHQ Risk Grade for Skybridge" height="20" /></a>

Terminal check:

terminal

curl -fsSL https://agentarmorhq.com/api/cli | node --input-type=module - check "alpic-ai-skybridge"

Share with your security lead

Need sign-off to use skybridge? Copy this note for Slack, a ticket or a pull request.

### AgentArmorHQ Security Review Memo: skybridge
- **Listing URL:** https://agentarmorhq.com/skills/alpic-ai-skybridge
- **Type:** AI agent skill
- **Risk Grade:** Grade C (Moderate risk signals)
- **Outside Security Advisories on File:** 0
- **Public Adoption:** 2.2k GitHub stars

#### Permission & Blast-Radius Signals
- **Local files:** No local folder access noted
- **Command execution:** No shell command runner noted
- **Network reach:** Connects to outside service API
- **Credentials:** Requires API key or token
- **Package source:** GitHub (alpic-ai/skybridge)

#### Recommended Hardened Setup
- **Source Repo:** https://github.com/alpic-ai/skybridge
- **Controls:** Pin an exact version in `.mcp.json`, scope access to a single workspace folder, and use a least-privilege read-only token where supported.

_Based on public adoption and transparency signals as of Oct 21, 2026. Our opinion, not a code audit or security guarantee._

Key facts

Type: AI agent skill
Publisher: alpic-ai
Source code: github.com/alpic-ai/skybridge
Est. context load: ~57 tokens idle · ~450 tokens when active (on-demand skill)
Popularity: 2.2k GitHub stars
Last updated: 2026-10-29
Last graded: 2026-10-21

Community

Discussions for Skybridge

Ask questions or share configuration tips. Governed by our Community Rules & Terms.

No posts match this filter yet.

Be the first to ask a question or share a working tip.

Was this listing for Skybridge helpful?

Check before you install, in Claude

Your assistant answers Block, Review or No known issues for any package before it installs it.

Get this check inside Claude