Threat
Internal System Prompt leaking to the user- Cursor CLI - Support / Bug Reports - Cursor - Community Forum
Publication date not yet evaluated · Added cursor.com
Page published
Coverage timeline
Single-source incident — one report is available.
Why it matters
System prompt leakage in an AI coding agent like Cursor CLI can expose internal instructions and tags that attackers could use to craft more effective prompt-injection or jailbreak attacks.
A Cursor Community Forum bug report from user Agrim_Sharma describes the Cursor CLI accidentally leaking its internal system prompt, including internal tags, to the user. The disclosure reportedly occurred after a prompt initially failed due to networking issues and was re-triggered once connectivity was restored.