{"data":{"id":"ac355ee9-ff2f-45ac-bfde-82e2679b84ff","title":"GHSA-2823-qmq8-rwvj: vLLM: Loose `cache_salt` validation lets a single request kill EngineCore on LMCache-MP deployments — uncaught downstream `ValueError` denial of service","summary":"vLLM's OpenAI-compatible request models (Completions, Chat Completions, Responses) accept a client-supplied `cache_salt` validated only as a non-empty string. With the built-in LMCache-MP KV connector enabled, the value reaches the scheduler's cache lookup unguarded, and the downstream LMCache `IPCCacheServerKey.__post_init__` raises an uncaught `ValueError` for `@`, `/`, `\\`, NUL or lengths over 128 characters. Because the exception is never caught on the scheduling path, a single request such as `cache_salt=\"/\"` kills EngineCore for all users.","solution":"N/A -- no mitigation discussed in source.","labels":["security"],"sourceUrl":"https://github.com/advisories/GHSA-2823-qmq8-rwvj","publishedAt":"2026-10-05T23:42:34.000Z","cveId":"CVE-2026-105756","cweIds":null,"cvssScore":null,"cvssSeverity":"medium","severity":"medium","attackType":["denial_of_service"],"issueType":"vulnerability","affectedPackages":["vllm@< 0.30.0 (fixed: 0.30.0)"],"affectedPackageNames":["vllm"],"affectedPackageRefs":["pypi:vllm"],"affectedVendors":[],"affectedVendorsRaw":["vLLM","LMCache"],"classifierModel":"claude-haiku-5-5","classifierPromptVersion":"v4","summaryPromptVersion":"v2","headline":null,"headlinePromptVersion":null,"cvssVector":null,"attackVector":null,"attackComplexity":null,"privilegesRequired":null,"userInteraction":null,"exploitMaturity":"unknown","epssScore":0.00332,"epssCheckedAt":"2026-11-20T06:10:05.584Z","kevDateAdded":null,"advisoryAliases":["GHSA-2823-qmq8-rwvj"],"affectedPackagesSource":null,"affectedPackagesCheckedAt":null,"patchAvailable":true,"disclosureDate":"2026-10-05T23:42:34.000Z","fixReleasedAt":"2026-09-22T05:22:21.647Z","daysToFix":-13,"fixCheckedAt":"2026-10-29T21:29:46.158Z","capecIds":null,"crossRefCount":1,"attackSophistication":"trivial","impactType":["availability"],"aiComponentTargeted":"inference","llmSpecific":true,"classifierConfidence":0.95,"researchCategory":null,"atlasIds":null,"fixes":[{"ecosystem":"pypi","name":"vllm","fixedVersion":"0.30.0","matchedVersion":"0.30.0","fixReleasedAt":"2026-09-22T05:22:21.647Z","daysToFix":-13,"match":"ecosystem","source":"tracked","status":"found","checkedAt":"2026-10-29T21:29:46.013Z"}]}}