{"id":"GHSA-78fp-cf4h-g36p","title":"Duplicate Advisory: vLLM introduced enhanced protection for CVE-2025-62164","summary":"Duplicate Advisory: vLLM introduced enhanced protection for CVE-2025-62164","severity":"high","cvss":8.8,"cwe":["CWE-20","CWE-787"],"vendor":"vllm","product":"vllm","ecosystem":"pip","affected":["vllm >= 0.10.2, < 0.13.0"],"patched":["vllm 0.13.0"],"published":"2026-06-20","updated":"2026-09-11","sourceUpdated":"2026-09-11T19:18:43Z","source":"GHSA","sourceUrl":"https://github.com/advisories/GHSA-78fp-cf4h-g36p","references":[{"url":"https://github.com/vllm-project/vllm/security/advisories/GHSA-mcmc-2m55-j8jj"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-56340"},{"url":"https://www.vulncheck.com/advisories/vllm-denial-of-service-via-unvalidated-multimodal-embeddings"},{"url":"https://access.redhat.com/security/cve/CVE-2026-56340"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2491060"},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2026/cve-2026-56340.json"},{"url":"https://github.com/advisories/GHSA-78fp-cf4h-g36p"}],"tags":["ghsa","pip"],"ingestedAt":"2026-09-11T19:57:09.310Z","slug":"GHSA-78fp-cf4h-g36p","body":"## Overview\n\n### Duplicate Advisory\n\nThis advisory has been withdrawn because it is a duplicate of GHSA-mcmc-2m55-j8jj. This link is maintained to preserve external references.\n\n### Original Description\n\nvLLM versions >= 0.10.2 and < 0.13.0 are missing sparse tensor validation in multimodal embeddings processing. Because PyTorch disables sparse tensor invariant checks by default, an attacker can submit crafted embedding requests with malformed (negative or out-of-bounds) tensor indices, when the prompt-embeds feature is enabled, to trigger crashes or resource exhaustion (denial of service), with potential for out-of-bounds/write-what-where memory corruption. This continues CVE-2025-62164, whose prior fix only disabled the feature by default rather than addressing the root cause.\n\n## Affected packages\n\n- `vllm >= 0.10.2, < 0.13.0`\n\n## Remediation\n\nUpgrade to a patched release:\n\n- `vllm 0.13.0`","depth":"twilight","depthScore":48,"depthScoreParts":{"impact":48.4,"likelihood":0,"exploitation":0,"ransomware":0},"changes":[]}