vLLM before 0.33.0 contains a path traversal vulnerability that allows malicious model publishers to redirect the served model and tokenizer by setting speculators_config verifier.name_or_path in config.json. Attackers can point this field at another local checkpoint directory to leak its tokenizer vocabulary via unauthenticated /detokenize requests and gain query access to private models.
{
"cna_assigner": "VulnCheck",
"cwe_ids": [
"CWE-22"
],
"osv_generated_from": "https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/130xxx/CVE-2026-130684.json"
}{
"extracted_events": [
{
"range": [
{
"introduced": "0"
},
{
"fixed": "0.33.0"
}
],
"source": "AFFECTED_FIELD",
"strategy": "StandardRange"
}
]
}