Summary
vLLM: Cross-User Data Leak Vulnerability
An integer overflow in the act_and_mul_kernel kernel can cause the output of one user request to be incorporated into the response of another request within the same inference batch. Under certain conditions, the last request in a batch can receive a partial or complete copy of the first user's inference result, resulting in cross-user data leakage.
Details
The root cause is an integer overflow in the expression blockIdx.x * 2 * d at https://github.com/vllm-project/vllm/blob/ff712f6447093d07747c88680b9d006b119f5890/csrc/activation_kernels.cu#L82.
As a result, the computation for one user (User A) can incorrectly consume input data from another user (User B). In particular, when 2^32 is divisible by d, the overflow can cause User A's output to contain portions of User B's inference result. In some cases, User B's response may be copied entirely into User A's response.
This constitutes a severe cross-user information disclosure vulnerability and is straightforward to trigger.
PoC
We reproduced the issue using meta-llama/Llama-3.2-1B-Instruct, for which d = 8192.
Using the following configuration:
Batch size: 17
Sequence length: 16384
The final response in the batch becomes an exact copy of the first response in the batch, demonstrating complete cross-user data leakage.
Versions
For versions prior and equal to 0.21.0, the bug is in csrc/activation_kernels.cu, and for versions later than 0.21.0, the bug is in csrc/libtorch_stable/activation_kernels.cu.
Impact
This vulnerability enables cross-user information disclosure. An attacker can intentionally craft requests that are processed within the same inference batch as a victim's request and cause the victim's inference output to be copied into the attacker's response.
As a result, sensitive information contained in another user's model response may be exposed to an unauthorized party.
An arithmetic operation produces a value that exceeds the integer type's maximum, causing it to wrap to an unexpected small value. Typical impact: incorrect size calculations leading to heap overflows or logic errors.
CVE-2026-73558 has a CVSS score of 5.3 (Medium). The vector is network-reachable, no privileges required, and user interaction required. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (0.27.0); upgrading removes the vulnerable code path.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
Kodem Kai can prioritize this vulnerability in your dependency tree and generate a fix recommendation.
Frequently Asked Questions
- What is CVE-2026-73558? CVE-2026-73558 is a medium-severity integer overflow or wraparound vulnerability in vllm (pip), affecting versions < 0.27.0. It is fixed in 0.27.0. An arithmetic operation produces a value that exceeds the integer type's maximum, causing it to wrap to an unexpected small value.
- How severe is CVE-2026-73558? CVE-2026-73558 has a CVSS score of 5.3 (Medium). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
- Which versions of vllm are affected by CVE-2026-73558? vllm (pip) versions < 0.27.0 is affected.
- Is there a fix for CVE-2026-73558? Yes. CVE-2026-73558 is fixed in 0.27.0. Upgrade to this version or later.
- Is CVE-2026-73558 exploitable, and should I be worried? Whether CVE-2026-73558 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-73558 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-73558? Upgrade
vllmto 0.27.0 or later.