Data exfiltration via filename prompt injection
Published Oct 14, 2025 · Updated Oct 14, 2025
Prompt injection in Windsurf 1.10.7 allows context-dependent attackers to exfiltrate local data through a crafted filename. In Write mode with the SWE-1 model, Windsurf appends a project filename to the user prompt and treats instructions embedded in that name as model directives. Exploitation requires a user to open and trust the crafted project and invoke Cascade; the model can then send project and host details through the approval-free Read Page tool.
Summary
What happened
Prompt injection in Windsurf 1.10.7 allows context-dependent attackers to exfiltrate local data through a crafted filename. In Write mode with the SWE-1 model, Windsurf appends a project filename to the user prompt and treats instructions embedded in that name as model directives. Exploitation requires a user to open and trust the crafted project and invoke Cascade; the model can then send project and host details through the approval-free Read Page tool.
The record
- CVE
- CVE-2025-36730
- Published
- Oct 14, 2025
- Updated
- Oct 14, 2025
- Vendor
- Windsurf
- Product
- Windsurf
- Classifications
- T1204.002
- Attack vector
- local
- Privileges
- unauthenticated
Timeline
How it unfolded
- Oct 14, 2025CVE publishedPublication date reported by the CVE source.
- Oct 14, 2025Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=1.10.7
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
- Tenable filename prompt-injection proof of conceptproof of concept · demonstrated
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo