{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-4944", "assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a", "state": "PUBLISHED", "assignerShortName": "@huntr_ai", "dateReserved": "2026-03-26T23:52:08.858Z", "datePublished": "2026-05-28T18:04:05.371Z", "dateUpdated": "2026-05-28T19:47:23.664Z"}, "containers": {"cna": {"title": "Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control", "providerMetadata": {"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a", "shortName": "@huntr_ai", "dateUpdated": "2026-05-28T18:04:05.371Z"}, "descriptions": [{"lang": "en", "value": "vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/model_executor/models/nemotron_vl.py` and `vllm/model_executor/models/kimi_k25.py`). This bypasses the user's explicit `--trust-remote-code=False` setting, enabling remote code execution via malicious HuggingFace model repositories. This issue is an incomplete fix for CVE-2025-66448 and CVE-2026-22807, as it affects separate code paths in model implementation files. Deployments loading NemotronVL or KimiK25 models are particularly impacted."}], "affected": [{"vendor": "vllm-project", "product": "vllm-project/vllm", "versions": [{"version": "unspecified", "status": "affected", "versionType": "custom", "lessThanOrEqual": "latest"}]}], "references": [{"url": "https://huntr.com/bounties/97f706f7-a852-49b2-a4eb-76811e611daf"}], "metrics": [{"cvssV3_0": {"version": "3.0", "attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "REQUIRED", "vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H", "baseScore": 8.8, "baseSeverity": "HIGH"}}], "problemTypes": [{"descriptions": [{"type": "CWE", "lang": "en", "description": "CWE-22 Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')", "cweId": "CWE-22"}]}], "source": {"advisory": "97f706f7-a852-49b2-a4eb-76811e611daf", "discovery": "EXTERNAL"}}, "adp": [{"references": [{"url": "https://huntr.com/bounties/97f706f7-a852-49b2-a4eb-76811e611daf", "tags": ["exploit"]}], "metrics": [{"other": {"type": "ssvc", "content": {"timestamp": "2026-05-28T19:46:54.159975Z", "id": "CVE-2026-4944", "options": [{"Exploitation": "poc"}, {"Automatable": "no"}, {"Technical Impact": "total"}], "role": "CISA Coordinator", "version": "2.0.3"}}}], "title": "CISA ADP Vulnrichment", "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-05-28T19:47:23.664Z"}}]}}

{"dataType": "CVE_RECORD", "dataVersion": "5.2", "cveMetadata": {"cveId": "CVE-2026-4944", "assignerOrgId": "c09c270a-b464-47c1-9133-acb35b22c19a", "state": "PUBLISHED", "assignerShortName": "@huntr_ai", "dateReserved": "2026-03-26T23:52:08.858Z", "datePublished": "2026-05-28T18:04:05.371Z", "dateUpdated": "2026-05-28T19:47:23.664Z"}, "containers": {"cna": {"title": "Hardcoded trust_remote_code=True in vllm-project/vllm Bypasses User Security Control", "providerMetadata": {"orgId": "c09c270a-b464-47c1-9133-acb35b22c19a", "shortName": "@huntr_ai", "dateUpdated": "2026-05-28T18:04:05.371Z"}, "descriptions": [{"lang": "en", "value": "vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/model_executor/models/nemotron_vl.py` and `vllm/model_executor/models/kimi_k25.py`). This bypasses the user's explicit `--trust-remote-code=False` setting, enabling remote code execution via malicious HuggingFace model repositories. This issue is an incomplete fix for CVE-2025-66448 and CVE-2026-22807, as it affects separate code paths in model implementation files. Deployments loading NemotronVL or KimiK25 models are particularly impacted."}], "affected": [{"vendor": "vllm-project", "product": "vllm-project/vllm", "versions": [{"version": "unspecified", "status": "affected", "versionType": "custom", "lessThanOrEqual": "latest"}]}], "references": [{"url": "https://huntr.com/bounties/97f706f7-a852-49b2-a4eb-76811e611daf"}], "metrics": [{"cvssV3_0": {"version": "3.0", "attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "REQUIRED", "vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H", "baseScore": 8.8, "baseSeverity": "HIGH"}}], "problemTypes": [{"descriptions": [{"type": "CWE", "lang": "en", "description": "CWE-22 Improper Limitation of a Pathname to a Restricted Directory ('Path Traversal')", "cweId": "CWE-22"}]}], "source": {"advisory": "97f706f7-a852-49b2-a4eb-76811e611daf", "discovery": "EXTERNAL"}}, "adp": [{"title": "CISA ADP Vulnrichment", "metrics": [{"other": {"type": "ssvc", "content": {"id": "CVE-2026-4944", "role": "CISA Coordinator", "options": [{"Exploitation": "poc"}, {"Automatable": "no"}, {"Technical Impact": "total"}], "version": "2.0.3", "timestamp": "2026-05-28T19:46:54.159975Z"}}}], "references": [{"url": "https://huntr.com/bounties/97f706f7-a852-49b2-a4eb-76811e611daf", "tags": ["exploit"]}], "providerMetadata": {"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "shortName": "CISA-ADP", "dateUpdated": "2026-05-28T19:47:16.494Z"}}]}}

{"cveTags": [], "descriptions": [{"lang": "en", "value": "vllm-project/vllm version 0.14.1 contains a vulnerability where the `trust_remote_code=True` parameter is hardcoded in two model implementation files (`vllm/model_executor/models/nemotron_vl.py` and `vllm/model_executor/models/kimi_k25.py`). This bypasses the user's explicit `--trust-remote-code=False` setting, enabling remote code execution via malicious HuggingFace model repositories. This issue is an incomplete fix for CVE-2025-66448 and CVE-2026-22807, as it affects separate code paths in model implementation files. Deployments loading NemotronVL or KimiK25 models are particularly impacted."}], "id": "CVE-2026-4944", "lastModified": "2026-05-28T19:16:42.677", "metrics": {"cvssMetricV30": [{"cvssData": {"attackComplexity": "LOW", "attackVector": "NETWORK", "availabilityImpact": "HIGH", "baseScore": 8.8, "baseSeverity": "HIGH", "confidentialityImpact": "HIGH", "integrityImpact": "HIGH", "privilegesRequired": "NONE", "scope": "UNCHANGED", "userInteraction": "REQUIRED", "vectorString": "CVSS:3.0/AV:N/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H", "version": "3.0"}, "exploitabilityScore": 2.8, "impactScore": 5.9, "source": "security@huntr.dev", "type": "Secondary"}]}, "published": "2026-05-28T19:16:42.677", "references": [{"source": "security@huntr.dev", "url": "https://huntr.com/bounties/97f706f7-a852-49b2-a4eb-76811e611daf"}], "sourceIdentifier": "security@huntr.dev", "vulnStatus": "Received", "weaknesses": [{"description": [{"lang": "en", "value": "CWE-22"}], "source": "security@huntr.dev", "type": "Primary"}]}

{}

{}