#cursoragent — Public Fediverse posts

"a single attack pattern lets a malicious repository achieve remote code execution through AI coding assistants. The agent is tricked into a benign-looking file copy that secretly overwrites its own config, and the next restart runs attacker code with full user privileges.

We confirmed the technique against #Claude Code, #Gemini CLI/Antigravity CLI, #CursorAgent CLI, GitHub #Copilot CLI, #Grok Build, and #OpenAI Codex CLI"

Ooops.

#GenAI

h/t @campuscodi

https://adversa.ai/blog/the-approval-prompt-is-lying-to-you-symlink-rce-in-five-ai-coding-agents-claude-code-cursor-antigravity-copilot-grok-build/