CVE-2026-71486 (GCVE-0-2026-71486)
Vulnerability from cvelistv5 – Published: 2026-08-17 20:13 – Updated: 2026-08-18 12:34
VLAI
EPSS
VEX
Title
vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds
Summary
vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts structures are processed by OnlineDerenderer and tokenizer.decode before max_model_len, max_tokens, max_num_seqs, or response-size limits are enforced, allowing an authenticated API client to consume excessive CPU and memory and produce oversized responses. This issue is fixed in version 0.26.0.
Severity
4.3 (Medium)
SSVC
Exploitation: none
Automatable: no
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-18 12:34 UTC
CWE
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/vllm-project/vllm/security/adv… | x_refsource_CONFIRM |
| https://github.com/vllm-project/vllm/pull/47260 | x_refsource_MISC |
| https://github.com/vllm-project/vllm/commit/8e61b… | x_refsource_MISC |
| https://github.com/vllm-project/vllm/releases/tag… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| vllm-project | vllm |
Affected:
< 0.26.0
|
guessed |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-71486",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-18T12:34:35.419144Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-18T12:34:44.986Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "vllm",
"vendor": "vllm-project",
"versions": [
{
"status": "affected",
"version": "\u003c 0.26.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts structures are processed by OnlineDerenderer and tokenizer.decode before max_model_len, max_tokens, max_num_seqs, or response-size limits are enforced, allowing an authenticated API client to consume excessive CPU and memory and produce oversized responses. This issue is fixed in version 0.26.0."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "LOW",
"baseScore": 4.3,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "NONE",
"privilegesRequired": "LOW",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-400",
"description": "CWE-400: Uncontrolled Resource Consumption",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-770",
"description": "CWE-770: Allocation of Resources Without Limits or Throttling",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-17T20:13:06.289Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff"
},
{
"name": "https://github.com/vllm-project/vllm/pull/47260",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/pull/47260"
},
{
"name": "https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b"
},
{
"name": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/vllm-project/vllm/releases/tag/v0.26.0"
}
],
"source": {
"advisory": "GHSA-8737-qx52-hjff",
"discovery": "UNKNOWN"
},
"title": "vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-71486",
"datePublished": "2026-08-17T20:13:06.289Z",
"dateReserved": "2026-08-06T19:56:23.725Z",
"dateUpdated": "2026-08-18T12:34:44.986Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-71486",
"date": "2026-08-24",
"epss": "0.00341",
"percentile": "0.26671"
},
"nvd": "{\"cve\":{\"id\":\"CVE-2026-71486\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-08-17T20:16:45.927\",\"lastModified\":\"2026-08-18T13:17:29.203\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts structures are processed by OnlineDerenderer and tokenizer.decode before max_model_len, max_tokens, max_num_seqs, or response-size limits are enforced, allowing an authenticated API client to consume excessive CPU and memory and produce oversized responses. This issue is fixed in version 0.26.0.\"}],\"affected\":[{\"source\":\"security-advisories@github.com\",\"affectedData\":[{\"vendor\":\"vllm-project\",\"product\":\"vllm\",\"versions\":[{\"version\":\"\u003c 0.26.0\",\"status\":\"affected\"}]}]}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L\",\"baseScore\":4.3,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"LOW\",\"userInteraction\":\"NONE\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"NONE\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"LOW\"},\"exploitabilityScore\":2.8,\"impactScore\":1.4}],\"ssvcV203\":[{\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\",\"ssvcData\":{\"timestamp\":\"2026-08-18T12:34:35.419144Z\",\"id\":\"CVE-2026-71486\",\"options\":[{\"exploitation\":\"none\"},{\"automatable\":\"no\"},{\"technicalImpact\":\"partial\"}],\"role\":\"CISA Coordinator\",\"version\":\"2.0.3\"}}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-400\"},{\"lang\":\"en\",\"value\":\"CWE-770\"}]}],\"references\":[{\"url\":\"https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/vllm-project/vllm/pull/47260\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/vllm-project/vllm/releases/tag/v0.26.0\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff\",\"source\":\"security-advisories@github.com\"}]}}",
"vulnrichment": {
"containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-71486\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-08-18T12:34:35.419144Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-08-18T12:34:40.788Z\"}}], \"cna\": {\"title\": \"vLLM: Derender endpoints decode caller-supplied GenerateResponse token IDs without output bounds\", \"source\": {\"advisory\": \"GHSA-8737-qx52-hjff\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 4.3, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:N/I:N/A:L\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"LOW\", \"privilegesRequired\": \"LOW\", \"confidentialityImpact\": \"NONE\"}}], \"affected\": [{\"vendor\": \"vllm-project\", \"product\": \"vllm\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 0.26.0\"}]}], \"references\": [{\"url\": \"https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff\", \"name\": \"https://github.com/vllm-project/vllm/security/advisories/GHSA-8737-qx52-hjff\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/vllm-project/vllm/pull/47260\", \"name\": \"https://github.com/vllm-project/vllm/pull/47260\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b\", \"name\": \"https://github.com/vllm-project/vllm/commit/8e61b646e2d157f9b93451fa048f9c8530c8a67b\", \"tags\": [\"x_refsource_MISC\"]}, {\"url\": \"https://github.com/vllm-project/vllm/releases/tag/v0.26.0\", \"name\": \"https://github.com/vllm-project/vllm/releases/tag/v0.26.0\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"vLLM is an inference and serving engine for large language models. Prior to 0.26.0, the /v1/completions/derender and /v1/chat/completions/derender endpoints accept caller-supplied GenerateResponse objects whose generate_responses, choices, token_ids, prompt_logprobs, logprobs.content, top_logprobs, and routed_experts structures are processed by OnlineDerenderer and tokenizer.decode before max_model_len, max_tokens, max_num_seqs, or response-size limits are enforced, allowing an authenticated API client to consume excessive CPU and memory and produce oversized responses. This issue is fixed in version 0.26.0.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-400\", \"description\": \"CWE-400: Uncontrolled Resource Consumption\"}]}, {\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-770\", \"description\": \"CWE-770: Allocation of Resources Without Limits or Throttling\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-08-17T20:13:06.289Z\"}}}",
"cveMetadata": "{\"cveId\": \"CVE-2026-71486\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-08-18T12:34:44.986Z\", \"dateReserved\": \"2026-08-06T19:56:23.725Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-08-17T20:13:06.289Z\", \"assignerShortName\": \"GitHub_M\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Loading…
Loading…