CVE-2026-47748 (GCVE-0-2026-47748)

Vulnerability from cvelistv5 – Published: 2026-06-16 17:11 – Updated: 2026-06-16 18:42
VLAI
Title
stable-diffusion.cpp: Out-of-bounds reads in PyTorch checkpoint pickle opcode parsing
Summary
stable-diffusion.cpp is a pure C/C++ library for running diffusion model (Stable Diffusion, Flux, Wan, Qwen Image, Z-Image, and more) inference. Versions prior to master-584-0a7ae07 are vulnerable to an out-of-bounds reads error through PyTorch checkpoint pickle opcode parsing. The pickle .ckpt parser in src/model.cpp did not consistently check that enough input remained before reading opcode arguments or advancing the parser buffer with a crafted or truncated .ckpt file. Throughout the pickle parser, opcode handlers advanced the parser position with expressions such as buffer += N without first checking that buffer + N <= buffer_end. A truncated file could therefore cause reads past the end of the metadata buffer. LibFuzzer found crashes in under one second using malformed checkpoint inputs. Any application using affected stable-diffusion.cpp releases to load untrusted .ckpt model files could be vulnerable. The attack requires the victim or application to load a .ckpt file from an untrusted source, such as a downloaded model from a model sharing site. This issue has been fixed in version master-584-0a7ae07. If developers are unable to immediately update their applications, they can work around this issue by ensuring they do not load .ckpt checkpoint files from untrusted sources. They should prefer trusted model sources and safer formats such as .safetensors where possible.
SSVC
Exploitation: poc Automatable: no Technical Impact: partial
CISA Coordinator (v2.0.3)
CWE
Assigner
References
Impacted products
Vendor Product Version
leejet stable-diffusion.cpp Affected: < master-584-0a7ae07
Create a notification for this product.
Show details on NVD website

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-47748",
                "options": [
                  {
                    "Exploitation": "poc"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-06-16T18:41:44.220881Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-06-16T18:42:49.132Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "references": [
          {
            "tags": [
              "exploit"
            ],
            "url": "https://github.com/leejet/stable-diffusion.cpp/security/advisories/GHSA-rx4w-x86j-vx57"
          }
        ],
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "stable-diffusion.cpp",
          "vendor": "leejet",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c master-584-0a7ae07"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "stable-diffusion.cpp is a pure C/C++ library for running diffusion model (Stable Diffusion, Flux, Wan, Qwen Image, Z-Image, and more) inference. Versions prior to master-584-0a7ae07 are vulnerable to an out-of-bounds reads error through PyTorch checkpoint pickle opcode parsing. The pickle .ckpt parser in src/model.cpp did not consistently check that enough input remained before reading opcode arguments or advancing the parser buffer with a crafted or truncated .ckpt file. Throughout the pickle parser, opcode handlers advanced the parser position with expressions such as buffer += N without first checking that buffer + N \u003c= buffer_end. A truncated file could therefore cause reads past the end of the metadata buffer. LibFuzzer found crashes in under one second using malformed checkpoint inputs. Any application using affected stable-diffusion.cpp releases to load untrusted .ckpt model files could be vulnerable. The attack requires the victim or application to load a .ckpt file from an untrusted source, such as a downloaded model from a model sharing site. This issue has been fixed in version master-584-0a7ae07. If developers are unable to immediately update their applications, they can work around this issue by ensuring they do not load .ckpt checkpoint files from untrusted sources. They should prefer trusted model sources and safer formats such as .safetensors where possible."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "LOW",
            "attackVector": "LOCAL",
            "availabilityImpact": "HIGH",
            "baseScore": 5.5,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "NONE",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-125",
              "description": "CWE-125: Out-of-bounds Read",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-06-16T17:11:15.143Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/leejet/stable-diffusion.cpp/security/advisories/GHSA-rx4w-x86j-vx57",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/leejet/stable-diffusion.cpp/security/advisories/GHSA-rx4w-x86j-vx57"
        },
        {
          "name": "https://github.com/leejet/stable-diffusion.cpp/commit/0a7ae07f948eff4611968a65a22bd7c7031ad74f",
          "tags": [
            "x_refsource_MISC"
          ],
          "url": "https://github.com/leejet/stable-diffusion.cpp/commit/0a7ae07f948eff4611968a65a22bd7c7031ad74f"
        }
      ],
      "source": {
        "advisory": "GHSA-rx4w-x86j-vx57",
        "discovery": "UNKNOWN"
      },
      "title": "stable-diffusion.cpp: Out-of-bounds reads in PyTorch checkpoint pickle opcode parsing"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-47748",
    "datePublished": "2026-06-16T17:11:15.143Z",
    "dateReserved": "2026-05-19T22:16:39.504Z",
    "dateUpdated": "2026-06-16T18:42:49.132Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-47748",
      "date": "2026-06-18",
      "epss": "0.00113",
      "percentile": "0.01697"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-47748\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-06-16T19:16:55.720\",\"lastModified\":\"2026-06-16T20:44:11.730\",\"vulnStatus\":\"Awaiting Analysis\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"stable-diffusion.cpp is a pure C/C++ library for running diffusion model (Stable Diffusion, Flux, Wan, Qwen Image, Z-Image, and more) inference. Versions prior to master-584-0a7ae07 are vulnerable to an out-of-bounds reads error through PyTorch checkpoint pickle opcode parsing. The pickle .ckpt parser in src/model.cpp did not consistently check that enough input remained before reading opcode arguments or advancing the parser buffer with a crafted or truncated .ckpt file. Throughout the pickle parser, opcode handlers advanced the parser position with expressions such as buffer += N without first checking that buffer + N \u003c= buffer_end. A truncated file could therefore cause reads past the end of the metadata buffer. LibFuzzer found crashes in under one second using malformed checkpoint inputs. Any application using affected stable-diffusion.cpp releases to load untrusted .ckpt model files could be vulnerable. The attack requires the victim or application to load a .ckpt file from an untrusted source, such as a downloaded model from a model sharing site. This issue has been fixed in version master-584-0a7ae07. If developers are unable to immediately update their applications, they can work around this issue by ensuring they do not load .ckpt checkpoint files from untrusted sources. They should prefer trusted model sources and safer formats such as .safetensors where possible.\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H\",\"baseScore\":5.5,\"baseSeverity\":\"MEDIUM\",\"attackVector\":\"LOCAL\",\"attackComplexity\":\"LOW\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"NONE\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"HIGH\"},\"exploitabilityScore\":1.8,\"impactScore\":3.6}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-125\"}]}],\"references\":[{\"url\":\"https://github.com/leejet/stable-diffusion.cpp/commit/0a7ae07f948eff4611968a65a22bd7c7031ad74f\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/leejet/stable-diffusion.cpp/security/advisories/GHSA-rx4w-x86j-vx57\",\"source\":\"security-advisories@github.com\"},{\"url\":\"https://github.com/leejet/stable-diffusion.cpp/security/advisories/GHSA-rx4w-x86j-vx57\",\"source\":\"134c704f-9b21-4f2e-91b3-4a467353bcc0\"}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-47748\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"poc\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-06-16T18:41:44.220881Z\"}}}], \"references\": [{\"url\": \"https://github.com/leejet/stable-diffusion.cpp/security/advisories/GHSA-rx4w-x86j-vx57\", \"tags\": [\"exploit\"]}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-06-16T18:41:31.496Z\"}}], \"cna\": {\"title\": \"stable-diffusion.cpp: Out-of-bounds reads in PyTorch checkpoint pickle opcode parsing\", \"source\": {\"advisory\": \"GHSA-rx4w-x86j-vx57\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 5.5, \"attackVector\": \"LOCAL\", \"baseSeverity\": \"MEDIUM\", \"vectorString\": \"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"LOW\", \"availabilityImpact\": \"HIGH\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"NONE\"}}], \"affected\": [{\"vendor\": \"leejet\", \"product\": \"stable-diffusion.cpp\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c master-584-0a7ae07\"}]}], \"references\": [{\"url\": \"https://github.com/leejet/stable-diffusion.cpp/security/advisories/GHSA-rx4w-x86j-vx57\", \"name\": \"https://github.com/leejet/stable-diffusion.cpp/security/advisories/GHSA-rx4w-x86j-vx57\", \"tags\": [\"x_refsource_CONFIRM\"]}, {\"url\": \"https://github.com/leejet/stable-diffusion.cpp/commit/0a7ae07f948eff4611968a65a22bd7c7031ad74f\", \"name\": \"https://github.com/leejet/stable-diffusion.cpp/commit/0a7ae07f948eff4611968a65a22bd7c7031ad74f\", \"tags\": [\"x_refsource_MISC\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"stable-diffusion.cpp is a pure C/C++ library for running diffusion model (Stable Diffusion, Flux, Wan, Qwen Image, Z-Image, and more) inference. Versions prior to master-584-0a7ae07 are vulnerable to an out-of-bounds reads error through PyTorch checkpoint pickle opcode parsing. The pickle .ckpt parser in src/model.cpp did not consistently check that enough input remained before reading opcode arguments or advancing the parser buffer with a crafted or truncated .ckpt file. Throughout the pickle parser, opcode handlers advanced the parser position with expressions such as buffer += N without first checking that buffer + N \u003c= buffer_end. A truncated file could therefore cause reads past the end of the metadata buffer. LibFuzzer found crashes in under one second using malformed checkpoint inputs. Any application using affected stable-diffusion.cpp releases to load untrusted .ckpt model files could be vulnerable. The attack requires the victim or application to load a .ckpt file from an untrusted source, such as a downloaded model from a model sharing site. This issue has been fixed in version master-584-0a7ae07. If developers are unable to immediately update their applications, they can work around this issue by ensuring they do not load .ckpt checkpoint files from untrusted sources. They should prefer trusted model sources and safer formats such as .safetensors where possible.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-125\", \"description\": \"CWE-125: Out-of-bounds Read\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-06-16T17:11:15.143Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-47748\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-06-16T18:42:49.132Z\", \"dateReserved\": \"2026-05-19T22:16:39.504Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-06-16T17:11:15.143Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}


Log in or create an account to share your comment.




Tags
Taxonomy of the tags.


Loading…

Loading…

Loading…

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…

Detection rules are retrieved from Rulezet.

Loading…

Loading…