CVE-2026-63764 (GCVE-0-2026-63764)

Vulnerability from cvelistv5 – Published: 2026-07-21 20:36 – Updated: 2026-07-21 20:36
VLAI
Title
lmdeploy Server-Side Request Forgery via HTTP Redirect Bypass of Private-IP Guard in Vision Image Fetch
Summary
lmdeploy's OpenAI-compatible API server contains a server-side request forgery vulnerability that allows unauthenticated attackers to access internal services and cloud metadata endpoints by supplying a crafted image_url that redirects to internal targets. Attackers can send a POST request to the chat completions endpoint with an image_url pointing to an attacker-controlled server that responds with an HTTP 302 redirect to internal addresses such as loopback or instance-metadata endpoints, bypassing the initial URL safety check because redirects are followed without re-validating each hop through the safety guard.
Severity
9.2 (Critical)
CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:L/SC:N/SI:H/SA:L
9.3 (Critical)
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N
CWE
  • CWE-918 - Server-Side Request Forgery (SSRF)
Assigner
References
Impacted products
Vendor Product Version
InternLM lmdeploy Unknown: 648df3b (git)
Create a notification for this product.
Date Public
2026-07-21 00:00
Credits
George Chen
Show details on NVD website
To clipboard 

{
  "containers": {
    "cna": {
      "affected": [
        {
          "defaultStatus": "affected",
          "product": "lmdeploy",
          "vendor": "InternLM",
          "versions": [
            {
              "status": "unknown",
              "version": "648df3b",
              "versionType": "git"
            }
          ]
        }
      ],
      "credits": [
        {
          "lang": "en",
          "type": "reporter",
          "value": "George Chen"
        }
      ],
      "datePublic": "2026-07-21T00:00:00.000Z",
      "descriptions": [
        {
          "lang": "en",
          "value": "lmdeploy\u0027s OpenAI-compatible API server contains a server-side request forgery vulnerability that allows unauthenticated attackers to access internal services and cloud metadata endpoints by supplying a crafted image_url that redirects to internal targets. Attackers can send a POST request to the chat completions endpoint with an image_url pointing to an attacker-controlled server that responds with an HTTP 302 redirect to internal addresses such as loopback or instance-metadata endpoints, bypassing the initial URL safety check because redirects are followed without re-validating each hop through the safety guard."
        }
      ],
      "metrics": [
        {
          "cvssV4_0": {
            "Automatable": "NOT_DEFINED",
            "Recovery": "NOT_DEFINED",
            "Safety": "NOT_DEFINED",
            "attackComplexity": "LOW",
            "attackRequirements": "NONE",
            "attackVector": "NETWORK",
            "baseScore": 9.2,
            "baseSeverity": "CRITICAL",
            "exploitMaturity": "NOT_DEFINED",
            "privilegesRequired": "NONE",
            "providerUrgency": "NOT_DEFINED",
            "subAvailabilityImpact": "LOW",
            "subConfidentialityImpact": "NONE",
            "subIntegrityImpact": "HIGH",
            "userInteraction": "NONE",
            "valueDensity": "NOT_DEFINED",
            "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:L/SC:N/SI:H/SA:L",
            "version": "4.0",
            "vulnAvailabilityImpact": "LOW",
            "vulnConfidentialityImpact": "NONE",
            "vulnIntegrityImpact": "HIGH",
            "vulnerabilityResponseEffort": "NOT_DEFINED"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        },
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 9.3,
            "baseSeverity": "CRITICAL",
            "confidentialityImpact": "HIGH",
            "integrityImpact": "LOW",
            "privilegesRequired": "NONE",
            "scope": "CHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N",
            "version": "3.1"
          },
          "format": "CVSS",
          "scenarios": [
            {
              "lang": "en",
              "value": "GENERAL"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-918",
              "description": "Server-Side Request Forgery (SSRF)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-07-21T20:36:58.372Z",
        "orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
        "shortName": "VulnCheck"
      },
      "references": [
        {
          "name": "GitHub Issue",
          "tags": [
            "product"
          ],
          "url": "https://github.com/InternLM/lmdeploy/issues/4761"
        },
        {
          "name": "Product",
          "tags": [
            "patch"
          ],
          "url": "https://github.com/InternLM/lmdeploy"
        },
        {
          "tags": [
            "third-party-advisory"
          ],
          "url": "https://www.vulncheck.com/advisories/lmdeploy-server-side-request-forgery-via-http-redirect-bypass-of-private-ip-guard-in-vision-image-fetch"
        }
      ],
      "source": {
        "discovery": "UNKNOWN"
      },
      "title": "lmdeploy Server-Side Request Forgery via HTTP Redirect Bypass of Private-IP Guard in Vision Image Fetch",
      "x_generator": {
        "engine": "vulncheck"
      }
    }
  },
  "cveMetadata": {
    "assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
    "assignerShortName": "VulnCheck",
    "cveId": "CVE-2026-63764",
    "datePublished": "2026-07-21T20:36:58.372Z",
    "dateReserved": "2026-07-18T12:34:08.780Z",
    "dateUpdated": "2026-07-21T20:36:58.372Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-63764\",\"sourceIdentifier\":\"disclosure@vulncheck.com\",\"published\":\"2026-07-21T21:16:53.350\",\"lastModified\":\"2026-07-21T21:16:53.350\",\"vulnStatus\":\"Received\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"lmdeploy\u0027s OpenAI-compatible API server contains a server-side request forgery vulnerability that allows unauthenticated attackers to access internal services and cloud metadata endpoints by supplying a crafted image_url that redirects to internal targets. Attackers can send a POST request to the chat completions endpoint with an image_url pointing to an attacker-controlled server that responds with an HTTP 302 redirect to internal addresses such as loopback or instance-metadata endpoints, bypassing the initial URL safety check because redirects are followed without re-validating each hop through the safety guard.\"}],\"affected\":[{\"source\":\"disclosure@vulncheck.com\",\"affectedData\":[{\"vendor\":\"InternLM\",\"product\":\"lmdeploy\",\"defaultStatus\":\"affected\",\"versions\":[{\"version\":\"648df3b\",\"versionType\":\"git\",\"status\":\"unknown\"}]}]}],\"metrics\":{\"cvssMetricV40\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"4.0\",\"vectorString\":\"CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:N/VC:N/VI:H/VA:L/SC:N/SI:H/SA:L/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X\",\"baseScore\":9.2,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"attackRequirements\":\"NONE\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"vulnConfidentialityImpact\":\"NONE\",\"vulnIntegrityImpact\":\"HIGH\",\"vulnAvailabilityImpact\":\"LOW\",\"subConfidentialityImpact\":\"NONE\",\"subIntegrityImpact\":\"HIGH\",\"subAvailabilityImpact\":\"LOW\",\"exploitMaturity\":\"NOT_DEFINED\",\"confidentialityRequirement\":\"NOT_DEFINED\",\"integrityRequirement\":\"NOT_DEFINED\",\"availabilityRequirement\":\"NOT_DEFINED\",\"modifiedAttackVector\":\"NOT_DEFINED\",\"modifiedAttackComplexity\":\"NOT_DEFINED\",\"modifiedAttackRequirements\":\"NOT_DEFINED\",\"modifiedPrivilegesRequired\":\"NOT_DEFINED\",\"modifiedUserInteraction\":\"NOT_DEFINED\",\"modifiedVulnConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedVulnIntegrityImpact\":\"NOT_DEFINED\",\"modifiedVulnAvailabilityImpact\":\"NOT_DEFINED\",\"modifiedSubConfidentialityImpact\":\"NOT_DEFINED\",\"modifiedSubIntegrityImpact\":\"NOT_DEFINED\",\"modifiedSubAvailabilityImpact\":\"NOT_DEFINED\",\"Safety\":\"NOT_DEFINED\",\"Automatable\":\"NOT_DEFINED\",\"Recovery\":\"NOT_DEFINED\",\"valueDensity\":\"NOT_DEFINED\",\"vulnerabilityResponseEffort\":\"NOT_DEFINED\",\"providerUrgency\":\"NOT_DEFINED\"}}],\"cvssMetricV31\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Primary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N\",\"baseScore\":9.3,\"baseSeverity\":\"CRITICAL\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"NONE\",\"scope\":\"CHANGED\",\"confidentialityImpact\":\"HIGH\",\"integrityImpact\":\"LOW\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":3.9,\"impactScore\":4.7}]},\"weaknesses\":[{\"source\":\"disclosure@vulncheck.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-918\"}]}],\"references\":[{\"url\":\"https://github.com/InternLM/lmdeploy\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://github.com/InternLM/lmdeploy/issues/4761\",\"source\":\"disclosure@vulncheck.com\"},{\"url\":\"https://www.vulncheck.com/advisories/lmdeploy-server-side-request-forgery-via-http-redirect-bypass-of-private-ip-guard-in-vision-image-fetch\",\"source\":\"disclosure@vulncheck.com\"}]}}"
  }
}



Log in or create an account to share your comment.




Tags
Taxonomy of the tags.





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.


Detection rules are retrieved from Rulezet.