Skip to content
Submit incident
AII-1001-48057
ReportedReported by fewer than three independent publishers, with no official finding.

Zed IDE MCP Configuration Arbitrary Code Execution

Mindgard identified a vulnerability in Zed IDE where malicious Model Context Protocol configurations in project settings can execute arbitrary shell commands with user privileges. The vulnerability was disclosed to Zed on November 16, 2025, and remediated through coordinated disclosure.

14 November 2025 Β· Zed Industries Β· Security and cyberattacks
14 November 2025
AII-1001-480572 sources ↓
Quick facts
Category
Security and cyberattacks
Source
mindgard.ai
Date
14 November 2025
Drafted by
Raidu Incident Detection

What happened

The Zed IDE loads Model Context Protocol (MCP) configurations from the settings.json file within a project's .zed subdirectory. A malicious MCP configuration can contain arbitrary shell commands that run on the host system with the privileges of the user running the IDE.

Reported impact

The vulnerability exposes users to arbitrary code execution when loading or interacting with a maliciously crafted source code repository, potentially triggered automatically without user interaction beyond opening the project.

Governance controls

Mindgard reported the vulnerability to Zed on November 16, 2025, and assisted in validating mitigations. Zed released a patched version of the software as part of a coordinated disclosure process.

Classification

Category
Security and cyberattacks
Industry
IT infrastructure and hosting
Harm status
Potential harm
Intent
Unknown
Timing
Post-deployment
AI systems
Zed IDE

Sources and evidence

This record was researched and written by the Index, based on the following original reporting.

mindgard.ai
Zed IDE MCP Configuration Arbitrary Code Execution
mindgard.ai
Mindgard Disclosure