Unauthenticated conversation API access via unchecked model
Published Sep 4, 2026 · Updated Sep 8, 2026
Missing authentication in FreeGPT WebUI 098db3dfeb41555c2ca9269df0f13e10ec1c35dc allows remote attackers to access its conversation API. The _conversation function in server/backend.py accepts a client-supplied model value and forwards the request to ChatCompletion.create without authenticating the caller. Any network client that can reach /backend-api/v2/conversation can submit prompts and consume the configured model service without an account or user interaction.
Summary
What happened
Missing authentication in FreeGPT WebUI 098db3dfeb41555c2ca9269df0f13e10ec1c35dc allows remote attackers to access its conversation API. The _conversation function in server/backend.py accepts a client-supplied model value and forwards the request to ChatCompletion.create without authenticating the caller. Any network client that can reach /backend-api/v2/conversation can submit prompts and consume the configured model service without an account or user interaction.
The record
- CVE
- CVE-2026-85702
- Published
- Sep 4, 2026
- Updated
- Sep 8, 2026
- Vendor
- ramon-victor
- Product
- FreeGPT WebUI
- Classifications
- CWE-306, CWE-287, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Sep 4, 2026CVE publishedPublication date reported by the CVE source.
- Sep 8, 2026Record 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=098db3dfeb41555c2ca9269df0f13e10ec1c35dc
What conditions does exploitation require?
What is affected?
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
- FreeGPT WebUI Backend Conversation API proof of conceptproof of concept · unverified
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