MediumVulnerabilityLLM-specific
CVE-2026-73558: vLLM integer overflow in activation kernel leaks batched inference results
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-73558
- Published
- Record updated
- Affected
- vllm < 0.27.0
- Fixed in
- 0.27.0
- released August 10, 2026, 3 days before disclosure
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.4%
Summary
CVE-2026-73558 affects vLLM, an inference and serving engine for large language models, prior to 0.27.0. An integer overflow in blockIdx.x * 2 * d in activation_kernels.cu can cause act_and_mul_kernel to consume another batched user's input. A request in the same inference batch may then receive a partial or complete copy of another user's inference result.
Mitigation
Fixed in version 0.27.0.
Affected packages in the Exposure Registry
Matched by package name and ecosystem. Each entry shows whether the package delegates to a language model and how many tracked packages depend on it.
- vllmPyPILLM dependency since 2023-08-25 · 15 tracked dependents
Topics
Related items
- MediumCVE-2026-124248: GPTranslate WordPress plugin stored cross-site scripting via comment parameterSimilar attack · NVD/CVE Database
- MediumAmazon: China-Linked Hackers’ AI Agents Exploited Medical Software Zero-DaySimilar attack · SecurityWeek
- MediumAttackers' AI Agents Found a Zero-Day in Medical-Imaging Software and Gained Root AccessSimilar attack · The Hacker News
- MediumCVE-2026-54026: LibreChat message injection via conversationId in request bodySimilar attack · NVD/CVE Database
- MediumCVE-2026-54046: LibreChat unauthenticated account enumeration via /api/user/verifySimilar attack · NVD/CVE Database