{"cve":"CVE-2026-105752","nvd":{"published":"2026-10-05T23:17:01.710","modified":"2026-10-08T01:29:51.587","status":"Analyzed","description":"vLLM is an inference and serving engine for large language models. Prior to 0.30.0, Harmony tool continuations submitted through \"POST /v1/responses\" requests rebuild the next-turn engine input without preserving the cache_salt value, placing the continuation prefix in the global unsalted cache namespace even when the caller enabled salting. On deployments with prefix caching enabled, which is the default, an authenticated tenant who can reconstruct a victim's low-entropy post-tool history can submit the same continuation and use the cached_tokens_per_turn count to determine whether the prefix was previously processed, defeating the intended tenant isolation of salted prefix caching. This issue is fixed in version 0.30.0.","cvss_v4":null,"cvss_v3":{"version":"3.1","vector":"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:L/A:N","score":3.1},"cwes":["CWE-200","CWE-524"],"references":["https://github.com/vllm-project/vllm/commit/6a2a2bb02b563b83f946012959fd3927984d072a","https://github.com/vllm-project/vllm/pull/50195","https://github.com/vllm-project/vllm/pull/51818","https://github.com/vllm-project/vllm/releases/tag/v0.30.0","https://github.com/vllm-project/vllm/security/advisories/GHSA-935w-9g4m-p28p"],"products":["vllm:vllm"],"source":"nvd","synced_at":"2026-10-19T22:57:46.668721662+00:00"},"epss":{"cve":"CVE-2026-105752","score":0.00216,"percentile":0.11984,"date":"2026-10-25"},"kev":null,"osv":[{"id":"GHSA-935w-9g4m-p28p","url":"https://osv.dev/vulnerability/GHSA-935w-9g4m-p28p","summary":"vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle","modified":"2026-10-15T14:56:01.064667635Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":["<0.30.0"],"fixed":["0.30.0"]}]},{"id":"PYSEC-2026-4308","url":"https://osv.dev/vulnerability/PYSEC-2026-4308","summary":"vLLM: Harmony tool continuations drop `cache_salt` — restoring a cross-tenant prefix-cache membership oracle","modified":"2026-10-15T14:45:14.136002872Z","packages":[{"ecosystem":"PyPI","name":"vllm","purl":"pkg:pypi/vllm","ranges":["<0.30.0"],"fixed":["0.30.0"]}]}],"attribution":["This product uses the NVD API but is not endorsed or certified by the NVD.","EPSS scores: FIRST Exploit Prediction Scoring System, https://www.first.org/epss","Known exploited vulnerabilities: CISA Known Exploited Vulnerabilities Catalog, https://www.cisa.gov/known-exploited-vulnerabilities-catalog","Package advisories: OSV (https://osv.dev), from the GitHub Advisory Database, PyPA, Go, RustSec and other ecosystem databases, under CC-BY 4.0 or CC0","CVE records: the CVE Program's CVE List (https://www.cve.org), under its terms of use (https://www.cve.org/Legal/TermsOfUse). CVE is a registered trademark of The MITRE Corporation; this product is not affiliated with the CVE Program."]}