CVE-2026-103395 (GCVE-0-2026-103395)
Vulnerability from cvelistv5
Published
2026-09-30 14:48
Modified
2026-09-30 19:38
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
CWE
  • CWE-502 - Deserialization of Untrusted Data
Summary
LightLLM through 1.2.0 visual_only deployments expose an unauthenticated RPyC service with allow_pickle enabled that deserializes attacker-supplied arguments in the remote_infer_images method. Attackers can reach the visual RPyC port and pass objects with __reduce__ methods to execute arbitrary code with service account privileges.
References
Impacted products
Vendor Product Version
ModelTC LightLLM Version: 0   ≤ 1.2.0
 Create a notification for this product.
Show details on NVD website

To clipboard 

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-103395",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "yes"
                  },
                  {
                    "Technical Impact": "total"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-09-30T19:37:06.254439Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-09-30T19:38:06.768Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/ModelTC/LightLLM/issues/1610"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "defaultStatus": "unaffected",
          "packageURL": "pkg:github/ModelTC/lightllm",
          "product": "LightLLM",
          "repo": "https://github.com/ModelTC/lightllm",
          "vendor": "ModelTC",
          "versions": [
            {
              "lessThanOrEqual": "1.2.0",
              "status": "affected",
              "version": "0",
              "versionType": "semver"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "finder",
          "value": "Mingkai Yu"
        },
        {
          "lang": "en",
          "type": "finder",
          "value": "Jiajia Liu"
        }
      ],
      "datePublic": "2026-09-30T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "LightLLM through 1.2.0 visual_only deployments expose an unauthenticated RPyC service with allow_pickle enabled that deserializes attacker-supplied arguments in the remote_infer_images method. Attackers can reach the visual RPyC port and pass objects with __reduce__ methods to execute arbitrary code with service account privileges."
        }
      ],
      "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": "2026-09-30T14:48:55.734Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "GitHub Issue #1610",
          "tags": [
            "issue-tracking"
          ],
          "url": "https://github.com/ModelTC/LightLLM/issues/1610"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/objs.py#L6-L11"
        },
        {
          "tags": [
            "technical-description"
          ],
          "url": "https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/visual_only_manager.py#L138-L140"
        },
        {
          "tags": [
            "product"
          ],
          "url": "https://github.com/ModelTC/LightLLM"
        },
        {
          "name": "VulnCheck Advisory: LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Visual-Only RPyC Service",
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-remote-code-execution-via-visual-only-rpyc-service"
        }
      ],
      "title": "LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Visual-Only RPyC Service",
      "x_generator": {
        "engine": "vulncheck-endgame"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-103395",
    "datePublished": "2026-09-30T14:48:55.734Z",
    "dateReserved": "2026-09-30T14:28:17.072Z",
    "dateUpdated": "2026-09-30T19:38:06.768Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "vulnrichment": {
      "containers": "{\"cna\": {\"providerMetadata\": {\"orgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"shortName\": \"VulnCheck\", \"dateUpdated\": \"2026-09-30T14:48:55.734Z\"}, \"datePublic\": \"2026-09-30T00:00:00.000Z\", \"title\": \"LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Visual-Only RPyC Service\", \"descriptions\": [{\"lang\": \"en\", \"value\": \"LightLLM through 1.2.0 visual_only deployments expose an unauthenticated RPyC service with allow_pickle enabled that deserializes attacker-supplied arguments in the remote_infer_images method. Attackers can reach the visual RPyC port and pass objects with __reduce__ methods to execute arbitrary code with service account privileges.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"description\": \"Deserialization of Untrusted Data\", \"cweId\": \"CWE-502\", \"type\": \"CWE\"}]}], \"affected\": [{\"vendor\": \"ModelTC\", \"product\": \"LightLLM\", \"defaultStatus\": \"unaffected\", \"packageURL\": \"pkg:github/ModelTC/lightllm\", \"versions\": [{\"version\": \"0\", \"status\": \"affected\", \"versionType\": \"semver\", \"lessThanOrEqual\": \"1.2.0\"}], \"repo\": \"https://github.com/ModelTC/lightllm\"}], \"metrics\": [{\"format\": \"CVSS\", \"cvssV4_0\": {\"version\": \"4.0\", \"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\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"LOW\", \"attackRequirements\": \"NONE\", \"privilegesRequired\": \"NONE\", \"userInteraction\": \"NONE\", \"vulnConfidentialityImpact\": \"HIGH\", \"vulnIntegrityImpact\": \"HIGH\", \"vulnAvailabilityImpact\": \"HIGH\", \"subConfidentialityImpact\": \"NONE\", \"subIntegrityImpact\": \"NONE\", \"subAvailabilityImpact\": \"NONE\", \"baseScore\": 9.3, \"baseSeverity\": \"CRITICAL\"}}, {\"format\": \"CVSS\", \"cvssV3_1\": {\"version\": \"3.1\", \"vectorString\": \"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H\", \"attackVector\": \"NETWORK\", \"attackComplexity\": \"LOW\", \"privilegesRequired\": \"NONE\", \"userInteraction\": \"NONE\", \"scope\": \"UNCHANGED\", \"confidentialityImpact\": \"HIGH\", \"integrityImpact\": \"HIGH\", \"availabilityImpact\": \"HIGH\", \"baseScore\": 9.8, \"baseSeverity\": \"CRITICAL\"}}], \"references\": [{\"url\": \"https://github.com/ModelTC/LightLLM/issues/1610\", \"tags\": [\"issue-tracking\"], \"name\": \"GitHub Issue #1610\"}, {\"url\": \"https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/objs.py#L6-L11\", \"tags\": [\"technical-description\"]}, {\"url\": \"https://github.com/ModelTC/lightllm/blob/v1.2.0/lightllm/server/visualserver/visual_only_manager.py#L138-L140\", \"tags\": [\"technical-description\"]}, {\"url\": \"https://github.com/ModelTC/LightLLM\", \"tags\": [\"product\"]}, {\"name\": \"VulnCheck Advisory: LightLLM through 1.2.0 Unauthenticated Remote Code Execution via Visual-Only RPyC Service\", \"tags\": [\"third-party-advisory\"], \"url\": \"https://www.vulncheck.com/advisories/lightllm-through-1.2.0-unauthenticated-remote-code-execution-via-visual-only-rpyc-service\"}], \"credits\": [{\"lang\": \"en\", \"value\": \"Mingkai Yu\", \"type\": \"finder\"}, {\"lang\": \"en\", \"value\": \"Jiajia Liu\", \"type\": \"finder\"}], \"x_generator\": {\"engine\": \"vulncheck-endgame\"}}, \"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-103395\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"yes\"}, {\"Technical Impact\": \"total\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-09-30T19:37:06.254439Z\"}}}], \"references\": [{\"url\": \"https://github.com/ModelTC/LightLLM/issues/1610\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-09-30T19:37:52.709Z\"}}]}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-103395\", \"assignerOrgId\": \"83251b91-4cc7-4094-a5c7-464a1b83ea10\", \"state\": \"PUBLISHED\", \"assignerShortName\": \"VulnCheck\", \"dateReserved\": \"2026-09-30T14:28:17.072Z\", \"datePublished\": \"2026-09-30T14:48:55.734Z\", \"dateUpdated\": \"2026-09-30T19:38:06.768Z\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.




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.