Developing story · 2 episodes · 25 Oct to 29 Oct
Hijacked AI Coding Assistants Threaten Developers
Researchers have demonstrated that AI coding agents can be compromised through malicious .md files, and later exposed vulnerabilities in the browsers of five AI coding assistants. The latest findings highlight ongoing security risks, prompting calls for stronger safeguards before these tools are widely adopted.
-
Researchers exploit flaws in five AI coding assistants’ browsers
Researchers at Forever Security found vulnerabilities in the embedded browsers of five AI coding tools: Cursor, GitHub Copilot, OpenAI’s Codex, Microsoft’s VS Code, and Anthropic’s Claude Desktop.…
1 source -
Researchers show AI coding agents can be hijacked via malicious agents.md files
Researchers at Forever Security discovered a security vulnerability where AI coding agents can be manipulated by malicious instruction files. They found a rogue AGENTS.md file in a customer's…
2 sources
Who and what
Forever SecurityOpenAIAnthropicBleepingComputerChromeEdgeCursorGitHubMicrosoftOpenAI CodexClaude CodeGal Weizman