Replit Enables App Store Publishing Without Coding Knowledge

Replit launches Mobile Apps feature for app creation without coding.

AI startup Replit has launched the Mobile Apps feature, allowing users to create applications through vibe coding and release them directly from the editor.

AI builds web apps well. Mobile apps have been harder.

Now, the inventor of React (the technology that AI uses to build apps), has a new announcement. pic.twitter.com/aDBXydRAjQ

— Replit ⠕ (@Replit) January 15, 2026

The new tool allows developers and entrepreneurs to “turn an idea into a working app in minutes and publish it to the App Store in a few days.”

The process is as follows:

1. The user describes the product in a text chat.
2. Replit generates the code in real-time.
3. The finished version is tested within the platform.

To upload to the app store, an Apple Developer account is required.

Before appearing in the app store, the software undergoes mandatory review. Apple is known for its strict requirements, but the company claims to process the majority of submissions within a day.

“Just tell the Replit Agent what you want to create, iterate in chat, preview instantly on your phone, and publish when ready,” the announcement states.

The Replit platform integrates Stripe support for project monetization. The startup’s valuation in the upcoming round could reach $9 billion (it was $3 billion in September).

What About Security?

Vibe coding is gaining popularity as a method for rapid development: it allows for app creation without deep technical knowledge. However, this approach raises concerns among cybersecurity experts.

A new study identified 69 vulnerabilities in 15 applications created using popular tools like Cursor, Claude Code, Codex, Replit, and Devin.

Tenzai specialists tested five AI agents for their ability to write secure code. For the sake of the experiment, each was tasked with creating a series of identical applications. The same prompts and technology stack were used.

Upon analyzing the results, analysts identified common behavior patterns and recurring failure patterns. On the positive side, agents effectively avoid certain classes of errors.

None of the generated solutions contained SQL injections or XSS vulnerabilities, which have been top-ranked in the OWASP list for years.

However, digital assistants showed weak results when dealing with complex architecture. They also allowed vulnerabilities in business logic.

“Human developers intuitively understand how workflows should function. Agents lack this ‘common sense’ and rely mainly on instructions,” the study notes.

For example, 4 out of 5 agents allowed attackers to create orders with negative amounts.

Cursor, Devin, and Replit made similar errors with pricing.

GPT-5.2 Codex in Cursor

A specialized version of the GPT-5 line for programming — GPT-5.2 Codex — is now available in Cursor.

GPT-5.2 Codex is now available in Cursor!

We believe it’s the frontier model for long-running tasks.

— Cursor (@cursor_ai) January 14, 2026

The company’s CEO, Michael Truell, reported that using the tool from OpenAI, the team created a browser that ran without interruption for one week.

“It consists of over 3 million lines of code across thousands of files. The rendering engine is written from scratch in Rust with HTML parsing, CSS cascading, layout, text formatting, drawing, and a customizable JS VM,” Truell stated.

According to metrics, GPT-5.2 slightly surpasses Opus 4.5 on SWE-Bench Pro.

Back in November 2025, Anthropic introduced Claude Opus 4.5 — “the world’s best model for programming, agents, and computer use.”