Vulnerability-Lookup

CVE-2026-41488 (GCVE-0-2026-41488)

Vulnerability from cvelistv5 – Published: 2026-04-24 20:57 – Updated: 2026-04-27 13:40

Title

angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding

Summary

LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai's _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch.

Severity ?

3.1 (Low)


                        
                          CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N

CWE

CWE-918 - Server-Side Request Forgery (SSRF)

Assigner

GitHub_M

References

URL

Tags

https://github.com/langchain-ai/langchain/securit…

x_refsource_CONFIRM

Impacted products

	Vendor	Product	Version
	langchain-ai	langchain-openai	Affected: < 1.1.14

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-41488",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-04-27T13:40:34.758273Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-04-27T13:40:42.065Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "langchain-openai",
          "vendor": "langchain-ai",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 1.1.14"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai\u0027s _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 3.1,
            "baseSeverity": "LOW",
            "confidentialityImpact": "LOW",
            "integrityImpact": "NONE",
            "privilegesRequired": "NONE",
            "scope": "UNCHANGED",
            "userInteraction": "REQUIRED",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-918",
              "description": "CWE-918: Server-Side Request Forgery (SSRF)",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-04-24T20:57:25.658Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r"
        }
      ],
      "source": {
        "advisory": "GHSA-r7w7-9xr2-qq2r",
        "discovery": "UNKNOWN"
      },
      "title": "angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-41488",
    "datePublished": "2026-04-24T20:57:25.658Z",
    "dateReserved": "2026-04-20T16:14:19.007Z",
    "dateUpdated": "2026-04-27T13:40:42.065Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "vulnerability-lookup:meta": {
    "epss": {
      "cve": "CVE-2026-41488",
      "date": "2026-04-28",
      "epss": "0.00028",
      "percentile": "0.07963"
    },
    "nvd": "{\"cve\":{\"id\":\"CVE-2026-41488\",\"sourceIdentifier\":\"security-advisories@github.com\",\"published\":\"2026-04-24T21:16:19.637\",\"lastModified\":\"2026-04-28T18:17:09.553\",\"vulnStatus\":\"Analyzed\",\"cveTags\":[],\"descriptions\":[{\"lang\":\"en\",\"value\":\"LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai\u0027s _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch.\"}],\"metrics\":{\"cvssMetricV31\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Secondary\",\"cvssData\":{\"version\":\"3.1\",\"vectorString\":\"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N\",\"baseScore\":3.1,\"baseSeverity\":\"LOW\",\"attackVector\":\"NETWORK\",\"attackComplexity\":\"HIGH\",\"privilegesRequired\":\"NONE\",\"userInteraction\":\"REQUIRED\",\"scope\":\"UNCHANGED\",\"confidentialityImpact\":\"LOW\",\"integrityImpact\":\"NONE\",\"availabilityImpact\":\"NONE\"},\"exploitabilityScore\":1.6,\"impactScore\":1.4}]},\"weaknesses\":[{\"source\":\"security-advisories@github.com\",\"type\":\"Primary\",\"description\":[{\"lang\":\"en\",\"value\":\"CWE-918\"}]}],\"configurations\":[{\"nodes\":[{\"operator\":\"OR\",\"negate\":false,\"cpeMatch\":[{\"vulnerable\":true,\"criteria\":\"cpe:2.3:a:langchain:langchain-openai:*:*:*:*:*:*:*:*\",\"versionEndExcluding\":\"1.1.14\",\"matchCriteriaId\":\"8089EE72-7257-4263-BF4E-8B429B2C0002\"}]}]}],\"references\":[{\"url\":\"https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r\",\"source\":\"security-advisories@github.com\",\"tags\":[\"Mitigation\",\"Vendor Advisory\"]}]}}",
    "vulnrichment": {
      "containers": "{\"adp\": [{\"title\": \"CISA ADP Vulnrichment\", \"metrics\": [{\"other\": {\"type\": \"ssvc\", \"content\": {\"id\": \"CVE-2026-41488\", \"role\": \"CISA Coordinator\", \"options\": [{\"Exploitation\": \"none\"}, {\"Automatable\": \"no\"}, {\"Technical Impact\": \"partial\"}], \"version\": \"2.0.3\", \"timestamp\": \"2026-04-27T13:40:34.758273Z\"}}}], \"providerMetadata\": {\"orgId\": \"134c704f-9b21-4f2e-91b3-4a467353bcc0\", \"shortName\": \"CISA-ADP\", \"dateUpdated\": \"2026-04-27T13:40:38.447Z\"}}], \"cna\": {\"title\": \"angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding\", \"source\": {\"advisory\": \"GHSA-r7w7-9xr2-qq2r\", \"discovery\": \"UNKNOWN\"}, \"metrics\": [{\"cvssV3_1\": {\"scope\": \"UNCHANGED\", \"version\": \"3.1\", \"baseScore\": 3.1, \"attackVector\": \"NETWORK\", \"baseSeverity\": \"LOW\", \"vectorString\": \"CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N\", \"integrityImpact\": \"NONE\", \"userInteraction\": \"REQUIRED\", \"attackComplexity\": \"HIGH\", \"availabilityImpact\": \"NONE\", \"privilegesRequired\": \"NONE\", \"confidentialityImpact\": \"LOW\"}}], \"affected\": [{\"vendor\": \"langchain-ai\", \"product\": \"langchain-openai\", \"versions\": [{\"status\": \"affected\", \"version\": \"\u003c 1.1.14\"}]}], \"references\": [{\"url\": \"https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r\", \"name\": \"https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r\", \"tags\": [\"x_refsource_CONFIRM\"]}], \"descriptions\": [{\"lang\": \"en\", \"value\": \"LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai\u0027s _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch.\"}], \"problemTypes\": [{\"descriptions\": [{\"lang\": \"en\", \"type\": \"CWE\", \"cweId\": \"CWE-918\", \"description\": \"CWE-918: Server-Side Request Forgery (SSRF)\"}]}], \"providerMetadata\": {\"orgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"shortName\": \"GitHub_M\", \"dateUpdated\": \"2026-04-24T20:57:25.658Z\"}}}",
      "cveMetadata": "{\"cveId\": \"CVE-2026-41488\", \"state\": \"PUBLISHED\", \"dateUpdated\": \"2026-04-27T13:40:42.065Z\", \"dateReserved\": \"2026-04-20T16:14:19.007Z\", \"assignerOrgId\": \"a0819718-46f1-4df5-94e2-005712e83aaa\", \"datePublished\": \"2026-04-24T20:57:25.658Z\", \"assignerShortName\": \"GitHub_M\"}",
      "dataType": "CVE_RECORD",
      "dataVersion": "5.2"
    }
  }
}

FKIE_CVE-2026-41488

Vulnerability from fkie_nvd - Published: 2026-04-24 21:16 - Updated: 2026-04-28 18:17

Severity ?

3.1 (Low) - CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N

Summary

References

	URL	Tags
	security-advisories@github.com	https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r	Mitigation, Vendor Advisory

Impacted products

	Vendor	Product	Version
	langchain	langchain-openai	*

JSON

To clipboard

{
  "configurations": [
    {
      "nodes": [
        {
          "cpeMatch": [
            {
              "criteria": "cpe:2.3:a:langchain:langchain-openai:*:*:*:*:*:*:*:*",
              "matchCriteriaId": "8089EE72-7257-4263-BF4E-8B429B2C0002",
              "versionEndExcluding": "1.1.14",
              "vulnerable": true
            }
          ],
          "negate": false,
          "operator": "OR"
        }
      ]
    }
  ],
  "cveTags": [],
  "descriptions": [
    {
      "lang": "en",
      "value": "LangChain is a framework for building agents and LLM-powered applications. Prior to 1.1.14, langchain-openai\u0027s _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch."
    }
  ],
  "id": "CVE-2026-41488",
  "lastModified": "2026-04-28T18:17:09.553",
  "metrics": {
    "cvssMetricV31": [
      {
        "cvssData": {
          "attackComplexity": "HIGH",
          "attackVector": "NETWORK",
          "availabilityImpact": "NONE",
          "baseScore": 3.1,
          "baseSeverity": "LOW",
          "confidentialityImpact": "LOW",
          "integrityImpact": "NONE",
          "privilegesRequired": "NONE",
          "scope": "UNCHANGED",
          "userInteraction": "REQUIRED",
          "vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N",
          "version": "3.1"
        },
        "exploitabilityScore": 1.6,
        "impactScore": 1.4,
        "source": "security-advisories@github.com",
        "type": "Secondary"
      }
    ]
  },
  "published": "2026-04-24T21:16:19.637",
  "references": [
    {
      "source": "security-advisories@github.com",
      "tags": [
        "Mitigation",
        "Vendor Advisory"
      ],
      "url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r"
    }
  ],
  "sourceIdentifier": "security-advisories@github.com",
  "vulnStatus": "Analyzed",
  "weaknesses": [
    {
      "description": [
        {
          "lang": "en",
          "value": "CWE-918"
        }
      ],
      "source": "security-advisories@github.com",
      "type": "Primary"
    }
  ]
}

GHSA-R7W7-9XR2-QQ2R

Vulnerability from github – Published: 2026-04-16 23:00 – Updated: 2026-04-16 23:00

Summary

langchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding

Details

Summary

langchain-openai's _url_to_size() helper (used by get_num_tokens_from_messages for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch.

The practical impact is limited because the fetched response body is passed directly to Pillow's Image.open() to extract dimensions — the response content is never returned, logged, or otherwise exposed to the caller. An attacker cannot exfiltrate data from internal services through this path. A potential risk is blind probing (inferring whether an internal host/port is open based on timing or error behavior).

Affected versions

langchain-openai < 1.1.14

Patched versions

langchain-openai >= 1.1.14 (requires langchain-core >= 1.2.31)

Affected code

File: libs/partners/openai/langchain_openai/chat_models/base.py — _url_to_size()

The vulnerable pattern was a validate-then-fetch with separate DNS resolution:

validate_safe_url(image_source, allow_private=False, allow_http=True)
# ... separate network operation with independent DNS resolution ...
response = httpx.get(image_source, timeout=timeout)

Fix

The fix replaces the validate-then-fetch pattern with an SSRF-safe httpx transport (SSRFSafeSyncTransport from langchain-core) that:

Resolves DNS once and validates all returned IPs against a policy (private ranges, cloud metadata, localhost, k8s internal DNS)
Pins the connection to the validated IP, eliminating the DNS rebinding window
Disables redirect following to prevent redirect-based SSRF bypasses

This fix was released in langchain-openai 1.1.14.

Severity ?

3.1 (Low)


                  
                    CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "PyPI",
        "name": "langchain-openai"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "1.1.14"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [],
  "database_specific": {
    "cwe_ids": [
      "CWE-918"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-04-16T23:00:12Z",
    "nvd_published_at": null,
    "severity": "LOW"
  },
  "details": "## Summary\n\n`langchain-openai`\u0027s `_url_to_size()` helper (used by `get_num_tokens_from_messages` for image token counting) validated URLs for SSRF protection and then fetched them in a separate network operation with independent DNS resolution. This left a TOCTOU / DNS rebinding window: an attacker-controlled hostname could resolve to a public IP during validation and then to a private/localhost IP during the actual fetch.\n\nThe practical impact is limited because the fetched response body is passed directly to Pillow\u0027s `Image.open()` to extract dimensions \u2014 the response content is never returned, logged, or otherwise exposed to the caller. An attacker cannot exfiltrate data from internal services through this path. A potential risk is blind probing (inferring whether an internal host/port is open based on timing or error behavior).\n\n## Affected versions\n\n- `langchain-openai` \u003c 1.1.14\n\n## Patched versions\n\n- `langchain-openai` \u003e= 1.1.14 (requires `langchain-core` \u003e= 1.2.31)\n\n## Affected code\n\n**File:** `libs/partners/openai/langchain_openai/chat_models/base.py` \u2014 `_url_to_size()`\n\nThe vulnerable pattern was a validate-then-fetch with separate DNS resolution:\n\n```python\nvalidate_safe_url(image_source, allow_private=False, allow_http=True)\n# ... separate network operation with independent DNS resolution ...\nresponse = httpx.get(image_source, timeout=timeout)\n```\n\n## Fix\n\nThe fix replaces the validate-then-fetch pattern with an SSRF-safe httpx transport (`SSRFSafeSyncTransport` from `langchain-core`) that:\n\n- Resolves DNS once and validates all returned IPs against a policy (private ranges, cloud metadata, localhost, k8s internal DNS)\n- Pins the connection to the validated IP, eliminating the DNS rebinding window\n- Disables redirect following to prevent redirect-based SSRF bypasses\n\nThis fix was released in langchain-openai 1.1.14.",
  "id": "GHSA-r7w7-9xr2-qq2r",
  "modified": "2026-04-16T23:00:12Z",
  "published": "2026-04-16T23:00:12Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/langchain-ai/langchain/security/advisories/GHSA-r7w7-9xr2-qq2r"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/langchain-ai/langchain"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:N/UI:R/S:U/C:L/I:N/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "langchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding"
}

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.

Action not permitted

CVE-2026-41488 (GCVE-0-2026-41488)

FKIE_CVE-2026-41488

GHSA-R7W7-9XR2-QQ2R

Summary

Affected versions

Patched versions

Affected code

Fix

Tags

Sightings

Nomenclature