Check out the latest research from IONIX: NEW! State of the WAF Report

New CVE Detected

CVE-2026-116176 – SSRF via X-Request-Id (P2pNcclConnector) – vLLM 0.9.2 to before 0.24.0

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

Summary

CVE-2026-116176 is a server-side request forgery (SSRF, CWE-918) vulnerability in vLLM versions 0.9.2 through 0.23.x. An API caller can supply a crafted X-Request-Id header that makes the P2pNcclConnector prefill worker open an outbound ZMQ connection to an attacker-controlled host. The CVE record lists a CVSS v4.0 score of 8.8 (High). It also lists a CVSS v3.1 score of 8.2 (High).

Technical details

  • Root cause: Two defects combine. OpenAIServing._base_request_id copies the HTTP X-Request-Id header verbatim without sanitization. P2pNcclConnector.parse_request_id then extracts an arbitrary host:port from it with a permissive regex that has no validation or scheme checks.
  • Trigger conditions: The P2pNcclConnector is non-default. It must be explicitly enabled through --kv-transfer-config (for example, "kv_connector":"P2pNcclConnector" with "kv_role":"kv_producer"). The attacker needs only a valid API key, or no key if authentication is disabled.
  • Attack vector: Network. The attacker sends an API request with an X-Request-Id header that embeds a malicious routing token.
  • Impact: The attacker can redirect the prefill worker’s connection to a host they control. The advisory says this can expose the NCCL communicator unique_id and KV-cache tensors, which include prompts and cached states. It can also disrupt worker availability by pointing the connection at an unresponsive host.

Affected software

  • vLLM 0.9.2 through 0.23.x (before 0.24.0), only when P2pNcclConnector is enabled.

Severity

  • CVSS v4.0: 8.8 (High) – CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:N/VA:L/SC:N/SI:N/SA:N
  • CVSS v3.1: 8.2 (High) – CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:L

Mitigation and recommended actions

  • Immediate: Upgrade to vLLM 0.24.0 or later. The fix removes the P2pNcclConnector entirely.
  • If you can’t patch: The advisory documents no workaround. It advises not enabling P2pNcclConnector until you have upgraded. Limit access to the vLLM API to trusted clients, and restrict outbound network connections from prefill workers.

References

Get a free Attack Surface scan to see if you’re exposed.

Get a free Attack Surface scan to see if you’re exposed.

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

Subscribe to Threat Center RSS

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

Get Real-Time CVE Alerts to Your Email

Be the first to know when new zero-days emerge