Skip to content
NewA calmer, faster ZeroHour

Plugin4Shell Lets Repository Owners Swap Pinned Plugin Code Across Four AI Coding Agents

The Hacker News ()4 min read3
AI summary · glm-5.3-flashSummaries by Vani AI

Air Security disclosed Plugin4Shell, letting repository owners swap version-locked plugins in Claude Code, Codex, GitHub Copilot, and Gemini CLI.

Air Security found that four widely used AI coding agents fetch version-locked plugin snapshots without verifying the code matches the pinned commit hash, letting repository owners serve different code via a hash-shaped branch name on hosts like Bitbucket or self-hosted git servers. Anthropic fixed the flaw in Claude Code 2.1.179 and OpenAI in Codex 0.146.0; GitHub Copilot has no fix, and Google will not patch the retired consumer Gemini CLI, pointing users to Antigravity. A Gemini CLI variant abuses a main branch named FETCH_HEAD, which GitHub's naming rules do not clearly block. Air reported a working test attack in June 2026; no CVE has been assigned, no vendor advisories exist, and no real-world exploitation has been observed.

Key facts
  • Agents fetch pinned commit snapshots but never verify retrieved code matches the locked hash
  • Hash-shaped branch names on Bitbucket or self-hosted git enable the swap; GitHub blocks such names
  • Gemini CLI variant abuses a main branch named FETCH_HEAD; Google won't patch, points to Antigravity
  • Swapped plugins run with user privileges, exposing files, credentials, and accessible systems
  • Air reported in June 2026; no CVE assigned, no vendor advisories, no observed exploitation
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

4 min read at thehackernews.com

A flaw in four widely used AI coding agents lets someone who controls a plugin's code repository swap the plugin an agent installs for a malicious one, even when the agent locked that plugin to a specific reviewed version, security firm Air Security said on Thursday. The firm said Anthropic has patched the flaw in Claude Code 2. 1.

The Hacker News

thehackernews.com

Read the full article at The Hacker News

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.