CVE-2026-85666 json
ogx 1.3.1 Server-Side Request Forgery via MCP tool server_url
published 2026-09-04 2 mo ago modified 2026-09-23 46 d ago also EUVD-2026-71122
- cvss
- 7.5
- version 3.1, CNA
- cisa kev
- Not listed
- not in CISA's catalog
- epss
- 0.7%
- EPSS 0.7% chance of exploitation in 30 days, percentile 54%
- public exploits
- 0
- none known
Summary
OGX (formerly Llama Stack, affected at commit fbe8e0f) contains an unauthenticated server-side request forgery vulnerability in the OpenAI-compatible POST /v1/responses endpoint. MCP tool definitions accept a server_url parameter (along with headers and authorization values) that is fetched server-side without destination validation; the existing validate_url_not_private() guard used for other URL inputs is not applied to server_url. On the default starter configuration, which runs without authentication, a remote unauthenticated attacker can cause the server to open connections to arbitrary internal addresses (including cloud metadata endpoints such as http://169.254.169.254/) and forward attacker-supplied headers and bearer tokens to those destinations.
Vendor advisories
What the vendors themselves say about their products: affected, fixed or not affected, and what to do.
red hat product security vex CVE-2026-85666 updated cvss 7.5
ogx: OGX: Information disclosure via Server-Side Request Forgery in MCP tool server_url
-
Red Hat Lightspeed Core lightspeed-core/rag-tool-cpu-rhel9, lightspeed-core/lightspeed-stack-rhel9, lightspeed-core/rag-tool-cuda-12.9-rhel9 Red Hat OpenShift AI (RHOAI) rhoai/odh-ogx-core-rhel9affected: workaround, no fix available
Red Hat CSAF VEX © Red Hat, Inc., from https://security.access.redhat.com/data/csaf/v2/vex/; changed: reduced to product statuses and remediations. CC BY 4.0 · csaf
CISA SSVC
- Exploitation
- none
- Automatable
- yes
- Technical impact
- partial
- Assessed
- 55 d ago
Exploit prediction
0.73% chance of exploitation in the next 30 days, higher than 54% of all scored CVEs (FIRST EPSS, 2026-11-08).
CVSS scores
| assigned by | version | score | vector |
|---|---|---|---|
| CNA | 4.0 | 8.7 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N |
| CNA | 3.1 | 7.5 | CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N |
| CNA | 4.0 | 8.7 | CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:N/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X |
Affected products
- ogx-ai ogx
Classification
- Weakness
-
- CWE-918 Server-Side Request Forgery
References
-
github.com
/ogx-ai/ogx/issues/6287
issue-tracking
-
github.com
/ogx-ai/ogx
product
-
github.com
/ogx-ai/ogx/blob/v1.3.1/src/ogx/providers/utils/tools/mcp.py
technical-description
-
vulncheck.com
/advisories/ogx-1.3.1-server-side-request-forgery-via-mcp-tool-server-url
third-party-advisory
Sources
- CVE List CVE-2026-85666
- NVD CVE-2026-85666
Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.