CVE-2026-44287: FastGPT JavaScript sandbox code execution via dynamic import bypass

Summary

CVE-2026-44287 affects FastGPT, an AI Agent building platform, before 4.15.0-beta1. The JavaScript sandbox worker at projects/code-sandbox/src/pool/worker.ts:356 blocks dynamic import() with the regex /\bimport\s*\(/.test(code), which misses a block comment placed between import and (, such as import/**/("child_process"). Because import() is not wrapped by the safeRequire Proxy, which only proxies require, an attacker can load child_process and call execSync to run arbitrary commands as uid=100(sandbox) inside the sandbox container.

Mitigation

Fixed in 4.15.0-beta1.

Topics

• AI agents

Related items

• InfoResearchers Used a Public OpenAI Model to Build a $250,000 Chrome Full-Chain Exploit in Six DaysSimilar attack · The Hacker News
• MediumAn AI Agent Found a Critical OTP Bypass in Production. The Attack Was the Easy Part.Similar attack · The Hacker News
• LowFBI arrests Saudi OpenAI employee who allegedly planted recording device in conference roomSimilar attack · CNBC Technology
• MediumVisual Studio Copilot and SSMS Remote Code Execution (CVE-2026-103572)Similar attack · Embrace The Red
• LowAnthropic warns self-replicating AI could spread to your smart devicesSimilar attack · BleepingComputer