HighVulnerabilityLLM-specific
CVE-2025-61593: Cursor CLI Agent prompt injection leads to code execution
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2025-61593
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.4%
Summary
CVE-2025-61593 affects Cursor, an AI-assisted code editor, in versions 1.7 and below. A flaw in how the Cursor CLI Agent protects sensitive files such as */.cursor/cli.json lets prompt injection modify their contents, enabling remote code execution, with full RCE possible on case-insensitive filesystems.
Mitigation
This issue is fixed in a commit, 25b418f, but has yet to be released as of October 3, 2025.
Related items
- InfoTop agent skill security resources — November 2026Similar attack · Adversa AI Blog
- InfoHow to Turn AI Red Team Findings Into Runtime ControlsSimilar attack · Straiker Blog
- MediumDocker Sandboxes vulnerability lets AI agents access sensitive files outside their sandbox (CVE-2026-103916) | Endor LabsSimilar attack · Endor Labs Blog
- MediumFree the Model, Sell the Gateway: Prompt Adware hidden in Jailbreak BundlesSimilar attack · Check Point Research
- InfoRight Tool, Wrong Parameters: Defending LLM Agents Against Parameter PoisoningSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)