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

Exploitation

No confirmed exploitation recorded. Patch Next marks exploitation only from CISA KEV.

CVSS

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

EPSS

• CVE-2026-41488: 0.16% estimated exploitation activity in the next 30 days; percentile 4.94 (FIRST EPSS, 2026-11-03). This is a model estimate, not proof of exploitation or customer exposure.

As published by the source; long descriptions are shortened.

Summary langchain-openai's urltosize() helper (used by getnumtokensfrommessages 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:…

Published by the source

16 Apr 2026, 23:00 UTC

Last modified by the source

6 Jun 2026, 01:15 UTC

Source last checked

26 Oct 2026, 13:44 UTC

1. Revision 2 · amended · 26 Oct 2026

   Amended from ghsa record GHSA-r7w7-9xr2-qq2r

2. Revision 1 · created · 24 Oct 2026

   Published from osv record GHSA-r7w7-9xr2-qq2r

Preview the exact text before you copy it. Commands are read-only suggestions; review them before running anything.

# Patch Next advisory brief: CVE-2026-41488

Advisory: langchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding
IDs: CVE-2026-41488, GHSA-r7w7-9xr2-qq2r
Record: https://patchnext.com/advisories/cve-2026-41488 (revision 2, source checked 26 Oct 2026, 13:44 UTC)
Inventory: none attached. This brief comes from a public page and does not say whether any deployment is affected.
Severity: Low (CVSS 3.1)
Exploitation: no confirmed exploitation recorded. Patch Next confirms exploitation only from CISA KEV.
Vendor response: Vendor fix available; fixed versions by package: langchain-openai 1.1.14. A vendor fix does not mean a deployment is fixed.

## Affected components
- PyPI langchain-openai: affected < 1.1.14; fixed in 1.1.14

## Suggested inspection (read-only)
- `python -m pip show langchain-openai`: prints the installed version. Run with the environment that serves production active.

## Supported action
Upgrade each affected component to a fixed version on its release line. For a transitive dependency, upgrade the parent package or add an override or constraint, then regenerate the lockfile. Redeploy every environment that ran an affected version.

## Required regression checks
- Run the test suite and a production build.
- Exercise the features that depend on langchain-openai.
- Repeat the inspection and confirm that only fixed versions remain installed.

## Rollback considerations
- Keep the previous lockfile and deployment artifact. Rolling back reinstates the vulnerable version, so apply any documented mitigation while you fix forward.

## Unresolved questions
- Which deployments run an affected version?
- Exploitation status can change. Check again before lowering the priority.
- Mark the work resolved only after the fixed version is verified in production.

## Sources
- Verified: https://osv.dev/vulnerability/GHSA-r7w7-9xr2-qq2r (OSV record GHSA-r7w7-9xr2-qq2r lists affected ranges: PyPI langchain-openai >=0 <1.1.14 (fixed))
- Verified: https://github.com/advisories/GHSA-r7w7-9xr2-qq2r (GitHub-reviewed advisory GHSA-r7w7-9xr2-qq2r lists affected ranges: PyPI langchain-openai >=0 <1.1.14)

Commands are suggestions: review each one before running it.