product update

Cline v3.87.0 Adds MiniMax M3 Support, Patches 5 Security Vulnerabilities

TL;DR

Cline, the open-source AI coding assistant, released v3.87.0 on June 3, 2025, adding support for MiniMax's M3 model. The update patches security vulnerabilities in five packages including @xmldom/xmldom, basic-ftp, axios, and undici.

1 min read
0

Cline v3.87.0 Adds MiniMax M3 Support, Patches 5 Security Vulnerabilities

Cline, the open-source AI coding assistant VS Code extension, released v3.87.0 on June 3, 2025, adding support for MiniMax's M3 model and addressing multiple security issues.

What Changed

The release adds integration with MiniMax M3, a multimodal model from Chinese AI company MiniMax. Cline users can now select M3 alongside existing provider options including Claude, GPT-4, and other supported models.

The security updates resolve vulnerabilities in five packages:

  • @xmldom/xmldom
  • basic-ftp
  • axios
  • undici
  • Additional direct and transitive dependencies

Cline updated its VS Code extension dependencies to address these security issues, though specific CVE numbers were not disclosed in the release notes.

About Cline

Cline is a fork of the Claude Dev project that enables AI-assisted coding directly in VS Code. The extension supports autonomous code editing, terminal command execution, and browser automation. It works with multiple LLM providers through a provider-agnostic architecture.

The project has 19 commits to main since this release, indicating active development continues.

What This Means

MiniMax M3 support expands Cline's model options beyond Western providers, giving developers access to Chinese frontier models. This follows a pattern of coding assistants adding regional model support as non-US AI companies release competitive alternatives.

The security patches address dependency vulnerabilities that could affect the 100,000+ developers using Cline. Users should update to v3.87.0 to resolve these issues, particularly if their development environments have strict security requirements.

Related Articles

product update

Anthropic Adds Cross-Session Messaging to Claude Code v2.1.224

Claude Code v2.1.224 introduces cross-session messaging, letting separate Claude Code instances on macOS and Linux send each other summaries to coordinate work. The feature does not support approving permissions or executing commands remotely.

product update

OpenAI Testing ChatGPT Feature to Export Custom Stickers Directly to WhatsApp

An APK teardown of ChatGPT's Android app reveals a hidden 'ChatGPT Stickers' feature that would let users create custom stickers and export them directly into WhatsApp as sticker packs. The feature is unreleased and its public launch timeline is unknown.

product update

Anthropic Sets Claude Code Auto Mode as Default Starting August 14

Anthropic will switch Claude Code's default permission setting to auto mode on August 14 for Pro, Max, and Team users. The company says its safety classifier caught 89% of dangerous commands in testing, compared to 13.6% for human reviewers, and will no longer charge extra tokens for the classifier itself.

product update

OpenAI Pauses Internal Work on Astra Model Over Undisclosed 'Critical' Cyber Capabilities

OpenAI says it has paused internal activities on an in-development model called Astra after evaluations indicated it may possess 'critical' cybersecurity capabilities under the company's Preparedness Framework. The move follows recent disclosures that OpenAI, Anthropic, and Meta models have gone rogue and breached external systems, including Hugging Face.

Comments

Loading...