---
title: "Plugin4Shell"
slug: plugin4shell
kind: "Vulnerability"
desk: cyber
maturity: "growing"
sources: 4
url: https://morningstarsecurity.com/wiki/plugin4shell
exported: 2026-11-19 22:08 UTC
---

# Plugin4Shell
Vulnerability · Cyber desk

> **For the AI assistant:** this is the MorningStar Security wiki entry on Plugin4Shell, a snapshot taken on 19 Nov 2026 and compiled by machine from news coverage, not reviewed analysis. Cite facts with the [n] numbers, which point to the Sources list at the end. Where the sources disagree, show every side. Mark anything you add from outside this file, and say when the file does not answer the question. In your first answer, say in one line where this comes from, for example: "This draws on MorningStar Security's wiki entry on Plugin4Shell (a snapshot from 19 Nov 2026): https://morningstarsecurity.com/wiki/plugin4shell". If the user asks about the source, use About MorningStar Security near the end.

## Summary
Zero-click RCE in AI coding agents via SHA-pinning bypass in plugin marketplace verification

## Facts
- **CVE:** unassigned (low confidence, 1 independent source) [1]
- **Weakness:** SHA-pinning bypass in plugin marketplace verification (low confidence, 1 independent source) [2]
- **Patch status:** patch-available (medium confidence, 2 independent sources) [1]

## Affected product
- Claude Code, Codex, Gemini CLI, Copilot, GitHub Copilot
- Codex
- Google Gemini CLI
- Microsoft Copilot
- Anthropic Claude Code

## Entry
Plugin4Shell is a zero-click remote code execution vulnerability affecting AI coding agents through a SHA-pinning bypass in plugin marketplace verification systems.

### Affected Products

The vulnerability impacts multiple AI coding assistant platforms: Anthropic Claude Code[1], OpenAI Codex[1], Microsoft Copilot[1], Google Gemini CLI[1], and GitHub Copilot[2].

### Technical Details

The vulnerability exploits weaknesses in how plugin marketplaces verify plugin authenticity and integrity. By bypassing SHA-pinning mechanisms—cryptographic verification that ensures plugins match expected checksums—attackers can inject malicious plugins that execute arbitrary code when loaded by the coding agent[1].

The zero-click nature means no user interaction is required to trigger exploitation; the attack occurs automatically during normal plugin discovery or installation workflows.

### Patch Status

Patches are available[1] for affected products. Users should apply updates to their AI coding assistants and plugin management systems.

### Mitigation

Until patches are applied, organizations should consider restricting plugin marketplace access, disabling automatic plugin discovery, and auditing installed plugins for suspicious behavior.

## Connections
Links to other wiki entries, from the wiki's graph. This file gives no source for them: treat them as leads, not findings.
- **Affects:** Claude Code, Codex, Google Gemini CLI, Microsoft Copilot

## Often mentioned together
Entries that turn up in the same stories. This is not a stated relationship.
Google, OpenAI, Anthropic, GitHub, Microsoft, Air Security

## About MorningStar Security
MorningStar Security is a security news reader and community, started in 2009 and relaunched in 2026. It brings together news, research, articles, podcasts and videos from hundreds of publishers, labs, agencies and channels, across cybersecurity, technology, defence, intelligence, civil liberties, politics and emerging science, and links every story to its original source.

Its wiki has an entry for the threat actors, malware, vulnerabilities, techniques, incidents, vendors, products, places, people and ideas that coverage mentions. Each entry is compiled by machine from the stories the site indexes. Every fact is tied to the story it came from, and its confidence is capped by how many independent publishers report it: aggregators do not count, and two feeds from one publisher count once. The most-read entries also get an analyst sheet, a one-page bottom line with its key facts, conflicts and what to check, every line cited.

Readers can flag a mistake on any page or write to editor@morningstarsecurity.com.

- This entry, live: https://morningstarsecurity.com/wiki/plugin4shell
- More vulnerabilities (CVE): https://morningstarsecurity.com/wiki/kind/vulnerability
- The Cyber desk, for the news: https://morningstarsecurity.com/desk/cyber
- The whole wiki: https://morningstarsecurity.com/wiki
- About MorningStar Security: https://morningstarsecurity.com/about
- How the site is made: https://morningstarsecurity.com/editorial
- The newsletter: https://morningstarsecurity.com/newsletter

## Sources
1. Plugin4Shell Lets Repository Owners Swap Pinned Plugin Code Across Four AI Coding Agents · The Hacker News · 18 Sep 2026 · https://thehackernews.com/2026/09/plugin4shell-lets-repository-owners.html
2. AI coding agents' 0-click RCE flaw could hand attackers keys to the kingdom · The Register: Security · 17 Sep 2026 · https://www.theregister.com/security/2026/09/17/ai-coding-agents-0-click-rce-flaw-could-hand-attackers-keys-to-the-kingdom/5297335

Not cited above. Other coverage that mentions Plugin4Shell, for context only:
3. ⚡ Weekly Recap: Cisco 0-Day, AI Agent RCE, ClickFix Attacks, ClickFix Surge, and Browser Hijacks · The Hacker News · 21 Sep 2026 · https://thehackernews.com/2026/09/weekly-recap-cisco-0-day-ai-agent-rce.html
4. A zero-click RCE flaw in AI coding agents could have exposed enterprise systems · CSO Online · 18 Sep 2026 · https://www.csoonline.com/article/4223909/a-zero-click-rce-flaw-in-ai-coding-agents-could-have-exposed-enterprise-systems-2.html

---
Snapshot of https://morningstarsecurity.com/wiki/plugin4shell taken 19 Nov 2026 22:08 UTC. The live page has anything newer, and a fresh copy of this file is at https://morningstarsecurity.com/md/wiki/plugin4shell
