Aim Labs discloses CurXecute vulnerability in Cursor IDE enabling RCE via MCP prompt injection (CVE-2025-54135)
Original title:When Public Prompts Turn Into Local Shells: ‘CurXecute’ – RCE in Cursor via MCP Auto‑Start
AI summary
Aim Labs (Cato) disclosed a high-severity vulnerability in Cursor IDE called CurXecute (CVE-2025-54135, score 8.6), where an externally hosted prompt injection can silently rewrite ~/.cursor/mcp. and execute arbitrary commands with user privileges, achieving RCE.
Key Takeaways
- Aim Labs (Cato) disclosed a high-severity vulnerability in Cursor IDE called CurXecute…
- 6),where an externally hosted prompt injection can silently rewrite ~/.
- cursor/mcp.
- and execute arbitrary commands with user privileges,achieving RCE.
Quick Facts
- Published
- Updated
- Source
- Cato AI Labs:AI安全原创研究
- Category
- Papers & Research
- AI score
- 72
原文给出完整的提示词注入到 RCE 攻击链细节和漏洞机理,读者可以据此审视 MCP 类 Agent 的运行时防护。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Aim Labs discloses CurXecute vulnerability in Cursor IDE enabling RCE via MCP prompt injection (CVE-2025-54135). January 8, 2025. https://new.nat6.net/en/news/cmtyo7jpl03v6rog0amn8zh9s/