CVE-2026-76850 (GCVE-0-2026-76850)
Vulnerability from cvelistv5
Published
2026-08-19 21:41
Modified
2026-08-21 11:21
Severity ?
9.3 (Critical) - CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N
9.8 (Critical) - CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
9.8 (Critical) - CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H
VLAI Severity ?
EPSS score ?
CWE
- CWE-502 - Deserialization of Untrusted Data
Summary
LMDeploy deserializes disaggregated-serving peer messages with pickle. The handle_zmq_recv coroutine in lmdeploy/pytorch/disagg/conn/engine_conn.py reads peer-to-peer cache-free requests with recv_pyobj(), which deserializes the received bytes with pickle.loads(), and the isinstance check against DistServeCacheFreeRequest runs only after deserialization has already completed. The peer that supplies those bytes is caller-controlled: p2p_connect passes remote_engine_endpoint_info.zmq_address from the request body to connect() on the ZMQ PULL socket, and the POST /distserve/p2p_initialize and /distserve/p2p_connect endpoints in lmdeploy/serve/openai/api_server.py apply no authentication unless the server is started with api_keys, which defaults to None. A remote attacker can direct an engine to pull from a ZMQ endpoint under their control and execute arbitrary code in the engine process. Deployments that do not enable disaggregated serving are not affected, because the receive loop is only started once the migration backend accepts the connection.
References
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-76850",
"options": [
{
"Exploitation": "poc"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-20T14:08:23.395015Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-20T14:08:52.458Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"references": [
{
"tags": [
"exploit"
],
"url": "https://github.com/InternLM/lmdeploy/issues/4804"
}
],
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"collectionURL": "https://pypi.org",
"defaultStatus": "unaffected",
"packageName": "lmdeploy",
"packageURL": "pkg:pypi/lmdeploy",
"product": "lmdeploy",
"repo": "https://github.com/InternLM/lmdeploy",
"vendor": "InternLM",
"versions": [
{
"lessThan": "0.16.0",
"status": "affected",
"version": "0.9.2",
"versionType": "semver"
}
]
}
],
"cpeApplicability": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:internlm:lmdeploy:*:*:*:*:*:*:*:*",
"versionEndExcluding": "0.16.0",
"versionStartIncluding": "0.9.2",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "reporter",
"value": "AAtomical"
}
],
"datePublic": "2026-07-29T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "LMDeploy deserializes disaggregated-serving peer messages with pickle. The handle_zmq_recv coroutine in lmdeploy/pytorch/disagg/conn/engine_conn.py reads peer-to-peer cache-free requests with recv_pyobj(), which deserializes the received bytes with pickle.loads(), and the isinstance check against DistServeCacheFreeRequest runs only after deserialization has already completed. The peer that supplies those bytes is caller-controlled: p2p_connect passes remote_engine_endpoint_info.zmq_address from the request body to connect() on the ZMQ PULL socket, and the POST /distserve/p2p_initialize and /distserve/p2p_connect endpoints in lmdeploy/serve/openai/api_server.py apply no authentication unless the server is started with api_keys, which defaults to None. A remote attacker can direct an engine to pull from a ZMQ endpoint under their control and execute arbitrary code in the engine process. Deployments that do not enable disaggregated serving are not affected, because the receive loop is only started once the migration backend accepts the connection."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "NETWORK",
"baseScore": 9.3,
"baseSeverity": "CRITICAL",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "NONE",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH"
},
"format": "CVSS"
},
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"format": "CVSS"
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-502",
"description": "Deserialization of Untrusted Data",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-21T11:21:12.965Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "GitHub Issue #4804",
"tags": [
"issue-tracking"
],
"url": "https://github.com/InternLM/lmdeploy/issues/4804"
},
{
"name": "fix(disagg): use JSON instead of pickle for P2P ZMQ requests",
"tags": [
"patch"
],
"url": "https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2"
},
{
"name": "Vulnerable recv_pyobj() call in v0.15.0",
"tags": [
"technical-description"
],
"url": "https://github.com/InternLM/lmdeploy/blob/v0.15.0/lmdeploy/pytorch/disagg/conn/engine_conn.py#L79"
},
{
"name": "Caller-controlled zmq_address passed to connect() in v0.15.0",
"tags": [
"technical-description"
],
"url": "https://github.com/InternLM/lmdeploy/blob/v0.15.0/lmdeploy/pytorch/disagg/conn/engine_conn.py#L61"
},
{
"name": "lmdeploy v0.16.0 Release Notes",
"tags": [
"release-notes"
],
"url": "https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0"
},
{
"tags": [
"product"
],
"url": "https://github.com/InternLM/lmdeploy"
},
{
"name": "VulnCheck Advisory: LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector",
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/lmdeploy-remote-code-execution-via-unsafe-pickle-deserialization-in-the-disaggregated-serving-peer-connector"
}
],
"title": "LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector",
"x_generator": {
"engine": "vulncheck-endgame"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-76850",
"datePublished": "2026-08-19T21:41:28.068Z",
"dateReserved": "2026-08-19T21:24:37.594Z",
"dateUpdated": "2026-08-21T11:21:12.965Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"vulnrichment": {
"containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-76850\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-08-20T14:08:23.395015Z\"}}}], \"references\": [{\"url\": \"https://github.com/InternLM/lmdeploy/issues/4804\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-08-20T14:08:36.764Z\"}}], \"cna\": {\"title\": \"LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector\", \"credits\": [{\"lang\": \"en\", \"type\": \"reporter\", \"value\": \"AAtomical\"}], \"metrics\": [{\"format\": \"CVSS\", \"cvssV4_0\": {\"version\": \"4.0\", \"baseScore\": 9.3, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"attackRequirements\": \"NONE\", \"privilegesRequired\": \"NONE\", \"subIntegrityImpact\": \"NONE\", \"vulnIntegrityImpact\": \"HIGH\", \"subAvailabilityImpact\": \"NONE\", \"vulnAvailabilityImpact\": \"HIGH\", \"subConfidentialityImpact\": \"NONE\", \"vulnConfidentialityImpact\": \"HIGH\"}}, {\"format\": \"CVSS\", \"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 9.8, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"CRITICAL\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\", \"integrityImpact\": \"HIGH\", \"userInteraction\": \"NONE\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"HIGH\"}}], \"affected\": [{\"repo\": \"https://github.com/InternLM/lmdeploy\", \"vendor\": \"InternLM\", \"product\": \"lmdeploy\", \"versions\": [{\"status\": \"affected\", \"version\": \"0.9.2\", \"lessThan\": \"0.16.0\", \"versionType\": \"semver\"}], \"packageURL\": \"pkg:pypi/lmdeploy\", \"packageName\": \"lmdeploy\", \"collectionURL\": \"https://pypi.org\", \"defaultStatus\": \"unaffected\"}], \"datePublic\": \"2026-07-29T00:00:00.000Z\", \"references\": [{\"url\": \"https://github.com/InternLM/lmdeploy/issues/4804\", \"name\": \"GitHub Issue #4804\", \"tags\": [\"issue-tracking\"]}, {\"url\": \"https://github.com/InternLM/lmdeploy/commit/f05b4ad8bf2e2d84101a1d63b3c44fadd99223b2\", \"name\": \"fix(disagg): use JSON instead of pickle for P2P ZMQ requests\", \"tags\": [\"patch\"]}, {\"url\": \"https://github.com/InternLM/lmdeploy/blob/v0.15.0/lmdeploy/pytorch/disagg/conn/engine_conn.py#L79\", \"name\": \"Vulnerable recv_pyobj() call in v0.15.0\", \"tags\": [\"technical-description\"]}, {\"url\": \"https://github.com/InternLM/lmdeploy/blob/v0.15.0/lmdeploy/pytorch/disagg/conn/engine_conn.py#L61\", \"name\": \"Caller-controlled zmq_address passed to connect() in v0.15.0\", \"tags\": [\"technical-description\"]}, {\"url\": \"https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0\", \"name\": \"lmdeploy v0.16.0 Release Notes\", \"tags\": [\"release-notes\"]}, {\"url\": \"https://github.com/InternLM/lmdeploy\", \"tags\": [\"product\"]}, {\"url\": \"https://www.vulncheck.com/advisories/lmdeploy-remote-code-execution-via-unsafe-pickle-deserialization-in-the-disaggregated-serving-peer-connector\", \"name\": \"VulnCheck Advisory: LMDeploy Remote Code Execution via Unsafe Pickle Deserialization in the Disaggregated Serving Peer Connector\", \"tags\": [\"third-party-advisory\"]}], \"x_generator\": {\"engine\": \"vulncheck-endgame\"}, \"descriptions\": [{\"lang\": \"en\", \"value\": \"LMDeploy deserializes disaggregated-serving peer messages with pickle. The handle_zmq_recv coroutine in lmdeploy/pytorch/disagg/conn/engine_conn.py reads peer-to-peer cache-free requests with recv_pyobj(), which deserializes the received bytes with pickle.loads(), and the isinstance check against DistServeCacheFreeRequest runs only after deserialization has already completed. The peer that supplies those bytes is caller-controlled: p2p_connect passes remote_engine_endpoint_info.zmq_address from the request body to connect() on the ZMQ PULL socket, and the POST /distserve/p2p_initialize and /distserve/p2p_connect endpoints in lmdeploy/serve/openai/api_server.py apply no authentication unless the server is started with api_keys, which defaults to None. A remote attacker can direct an engine to pull from a ZMQ endpoint under their control and execute arbitrary code in the engine process. Deployments that do not enable disaggregated serving are not affected, because the receive loop is only started once the migration backend accepts the connection.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-502\", \"description\": \"Deserialization of Untrusted Data\"}]}], \"cpeApplicability\": [{\"nodes\": [{\"negate\": false, \"cpeMatch\": [{\"criteria\": \"cpe:2.3:a:internlm:lmdeploy:*:*:*:*:*:*:*:*\", \"vulnerable\": true, \"versionEndExcluding\": \"0.16.0\", \"versionStartIncluding\": \"0.9.2\"}], \"operator\": \"OR\"}]}], \"providerMetadata\": {\"orgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"shortName\": \"VulnCheck\", \"dateUpdated\": \"2026-08-21T11:21:12.965Z\"}}}",
"cveMetadata": "{\"cveId\": \"CVE-2026-76850\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-08-21T11:21:12.965Z\", \"dateReserved\": \"2026-08-19T21:24:37.594Z\", \"assignerOrgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"datePublished\": \"2026-08-19T21:41:28.068Z\", \"assignerShortName\": \"VulnCheck\"}",
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Sightings
| Author | Source | Type | Date |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or seen somewhere by the user.
- Confirmed: The vulnerability is confirmed from an analyst perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: This vulnerability was exploited and seen by the user reporting the sighting.
- Patched: This vulnerability was successfully patched by the user reporting the sighting.
- Not exploited: This vulnerability was not exploited or seen by the user reporting the sighting.
- Not confirmed: The user expresses doubt about the veracity of the vulnerability.
- Not patched: This vulnerability was not successfully patched by the user reporting the sighting.
Loading…
Loading…