MediumVulnerabilityLLM-specific
CVE-2025-36730: Windsurf prompt injection via crafted file name in Write mode
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2025-36730
- Published
- Record updated
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.2%
Summary
CVE-2025-36730 describes a prompt injection vulnerability in Windsurft version 1.10.7 when used in Write mode with the SWE-1 model. An attacker can create a file name that is appended to the user prompt, causing Windsurf to follow instructions embedded in that name. Tenable Network Security, Inc. is the CNA, rating it CVSS 4.0 MEDIUM (4.6), and NIST has not yet provided an assessment.
Mitigation
The source does not state a fix yet. Check the original advisory for updates.
Topics
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)