CVE-2026-94626 — Vllm-project
Fix: vllm-project/vllm#51137CVE-2026-94626 is a CWE-789 vulnerability. No vendor fix is recorded yet; mitigation options are listed below.
vLLM through 0.29.0 Memory Exhaustion via Unvalidated NIXL tp_size
EPSS Exploitation Probability
EPSS (Exploit Prediction Scoring System) is a daily probability model maintained by FIRST.org. It estimates the likelihood a CVE will be exploited in production environments within the next 30 days, derived from real-world threat intelligence signals.
Description
vLLM through 0.29.0 fails to validate the tp_size parameter in kv_transfer_params on OpenAI-compatible completion endpoints, allowing attackers to allocate unbounded memory. Attackers can supply arbitrary tp_size values in prefill/decode disaggregated deployments to exhaust memory and trigger kernel OOM-kill of the decode worker process.
Detection & mitigation playbook
VulnerabilityDetect
Identify every host running the affected component and compare the installed build against the fixed version below — for source-built or distro-packaged software the version string, not a lockfile, is the source of truth (`dpkg -l`, `rpm -q`, or the binary's own `--version`). Because exploitation targets the running service rather than your application code, O3 also flags the exploit behaviour from runtime telemetry and egress traffic.
Remediation status
No fixed release is recorded for CVE-2026-94626 yet. Track the upstream advisory, and apply the exposure-reduction steps below in the meantime.
Mitigate without a patch
Reduce reachability while you patch: restrict network access to the service to trusted sources, disable or gate the affected component where your deployment allows it, and add a WAF/IPS signature if one exists for CVE-2026-94626. O3's runtime protection blocks the cwe-789 flaw at execution, which holds the line on hosts you cannot patch immediately.
How O3 protects you
O3 detects and blocks CVE-2026-94626 exploitation at runtime with eBPF exploit-chain detection, plus L7 egress monitoring that catches a post-exploitation callback and cuts the attacker's outbound channel.
Tailored to CVE-2026-94626. Runtime protection reduces exposure until a permanent patch is applied and verified — it complements patching, it doesn't replace it.
Frequently Asked Questions
Is CVE-2026-94626 in your dependencies?
O3 Security finds CVE-2026-94626 across dependencies, including transitive ones, and its impact-aware SCA ranks findings by whether your code actually calls the vulnerable path.