CVE-2026-85666: SSRF (CVSS 7.5)

Description

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.

Is your site exposed to CVE-2026-85666?

Run a free security scan — no signup, results in seconds.

CVSS v3.1 Score

7.5

HIGH

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N

EPSS — Exploit Prediction

0.0042

Probability of exploitation

0.35%

Percentile rank

EPSS estimates the probability that this vulnerability will be exploited in the wild within the next 30 days. A higher score means more likely to be exploited.

Weakness Type (CWE)

CWE-918 Server-Side Request Forgery (SSRF)

References

Other References

https://github.com/ogx-ai/ogx https://github.com/ogx-ai/ogx/blob/v1.3.1/src/ogx/providers/utils/tools/mcp.py https://github.com/ogx-ai/ogx/issues/6287 https://www.vulncheck.com/advisories/ogx-1.3.1-server-side-request-forgery-via-mcp-tool-server-url

Frequently Asked Questions

What is CVE-2026-85666? +

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. It has a CVSS v3.1 base score of 7.5 (HIGH).

How severe is CVE-2026-85666? +

CVE-2026-85666 has a CVSS v3.1 score of 7.5 out of 10, rated HIGH. This is a high-severity vulnerability that should be prioritized for patching. The EPSS score is 0.0042, placing it in the 0th percentile for exploitation probability.

How do I check if I'm vulnerable to CVE-2026-85666? +

You can use Secably's free Website Scanner to check your website for known vulnerabilities. For infrastructure scanning, use the Port Scanner to identify exposed services that may be affected. Check the vendor advisories linked above for specific patch and version information.

Related Vulnerabilities

CVE-2026-42336

MaxKB is an open-source AI assistant for enterprise. MaxKB 2.8.0 and prior are vulnerable to a server-side request forgery (SSRF) …

CVE-2026-41682

pupnp is an SDK for development of UPnP device and control point applications. Prior to version 1.18.5, pupnp is vulnerable …

CVE-2026-44286

FastGPT is an AI Agent building platform. Prior to version 4.14.17, an unauthenticated Server-Side Request Forgery (SSRF) vulnerability allows attackers …

CVE-2026-41172

Squidex is an open source headless content management system and content management hub. Prior to version 7.23.0, an SSRF vulnerability …

CVE-2026-45412

MaxKB is an open-source AI assistant for enterprise. Prior to 2.9.1, SSRF via work_flow_template Import. Authenticated users can supply arbitrary …

CVE-2026-41129

Craft CMS is a content management system (CMS). Versions on the 4.x branch through 4.17.8 and the 5.x branch through …

CVE-2026-85666