Live Exposure Defense: From CVE to Confirmed Exposure in 12 Hours – See more

Back
New CVE Detected

CVE-2026-85666 – Unauthenticated SSRF – OGX (ogx-ai/ogx) ≤ 1.3.1

Be the first to know when new zero-days emerge:

Subscribe to Email Alerts
Subscribe to RSS Feed

Summary

CVE-2026-85666 is an unauthenticated Server-Side Request Forgery (SSRF) vulnerability affecting OGX, an OpenAI-compatible inference/agent server published as the ogx PyPI package by ogx-ai. The flaw resides in the POST /v1/responses endpoint, where MCP (Model Context Protocol) tool definitions accept a server_url parameter that the server fetches without validating the destination. The vulnerability carries a CVSS v4.0 base score of 8.7 (High) and a CVSS v3.1 base score of 7.5 (High), and requires no authentication or user interaction to exploit.

Technical details

  • Root cause: When processing MCP tool definitions submitted to the /v1/responses API, OGX takes the attacker-supplied server_url field and issues a server-side HTTP request to it without validating or restricting the destination (no allow-list, no blocking of internal/link-local/loopback ranges).
  • Trigger conditions: An attacker sends a crafted request to the OpenAI-compatible POST /v1/responses endpoint, defining an MCP tool whose server_url points to an internal or cloud-internal address.
  • Attack vector: Network — the endpoint is reachable remotely and requires no prior authentication (PR:N) or user interaction (UI:N).
  • Impact: Because the request is made server-side, an attacker can pivot into internal networks, reach services not otherwise exposed to the internet, and query cloud instance metadata services (e.g., to retrieve temporary cloud credentials). Per the CVSS vectors, the primary impact is a high loss of confidentiality (C:H), with no direct impact on integrity or availability.

Affected software

  • ogx (PyPI package, ogx-ai) — versions 0 through 1.3.1 (all releases up to and including 1.3.1)
  • Versions after 1.3.1 are reported as not affected

Severity

  • CVSS v3.1: 7.5 (High) — CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N
  • CVSS v4.0: 8.7 (High) — 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
  • CWE-918: Server-Side Request Forgery (SSRF)

Mitigation and recommended actions

  • Immediate: Upgrade ogx to a version newer than 1.3.1, where this issue is fixed.
  • If patching is not immediately possible:
    • Restrict outbound network access from the OGX server host so it cannot reach internal-only address ranges, loopback addresses, or the cloud metadata endpoint (e.g., 169.254.169.254).
    • Place the /v1/responses endpoint behind an authenticating reverse proxy or API gateway and restrict access to trusted callers only, until the underlying MCP tool server_url handling is patched.
    • Enforce hardened cloud metadata service protections (e.g., IMDSv2 or equivalent token-based metadata access) on hosts running OGX to reduce the impact of any SSRF-driven metadata queries.
    • Monitor outbound requests from the OGX service for connections to internal or metadata IP ranges as an indicator of exploitation attempts.

References

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report

How IONIX’s External Exposure Management Platform Detects and Validates
Zero-Days to Shrink MTTR

1

Map your entire attack surface (continously)

IONIX uses multi-factor discovery methods, including DNS analysis, certificate mapping, metadata inspection, and more, to automatically map every internet-facing asset across your environment. This includes cloud instances, third-party platforms, shadow IT, and even forgotten infrastructure that traditional tools miss.

2

Monitor for new CVEs

Dozens of threat intel feeds using agentic technology are continuously analyzed to detect the appearance of proof-of-concept code, exploit kits, and indicators of active targeting. IONIX goes further by applying AI to proactively evaluate whether emerging vulnerabilities are likely to be exploited, even before PoCs go public.

3

Identify Potential External Exposures

Not all CVEs matter. IONIX filters vulnerabilities by asking attacker-centric questions: Can it be reached from the internet? Does it require authentication? Is it being exploited in the wild? This dramatically reduces noise and focuses teams on threats that can actually be weaponized.

4

Create Safe, Scalable Exploit Validations

IONIX transforms real-world PoCs into safe, non-intrusive test payloads that can be run in production environments without disruption. These simulations are precisely targeted to the systems that are vulnerable, ensuring rapid validation without unnecessary load.

5

Execute Exploit Validations

By combining context about software stack, versioning, exposure status, and reachability, IONIX ensures that only the right payloads are executed against the right assets, maximizing efficiency and minimizing risk.

6

Drive Fast and Actionable Remediation

Results are routed through integrations with ticketing, SOAR, and SIEM tools. Issues are written in plain language, bundled into remediation clusters, and prioritized based on asset criticality, exploitability, and blast radius. This shortens mean time to remediation (MTTR) and empowers teams to act with confidence.

Are you exposed?

Get a free report of your organization’s exposure to this CVE and threat

  • Mapping of all Assets with this Technology
  • Identification of potentially exposed assets to this CVE
  • Confirmation of verified exploitable assets
Get Exposure Report
Close

Subscribe to Threat Center RSS

Copy/paste the link below into your preferred RSS reader or follow these instructions to subscribe to Slack alerts.

Open RSS feedSlack setup instructions

Close

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge