Advisory

GHSA-r7w7-9xr2-qq2r

Also known as: CVE-2026-41488, PYSEC-2026-76

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

Low Basis: The source's own band: LOW

Dates

Published
2026-04-16 23:00 UTC
Modified
2026-06-06 01:15 UTC

Affected packages and fixes

langchain-openai

PyPI · All systems

Affected

  • introduced 0, fixed 1.1.14 (ecosystem)

Fixed versions

1.1.14

Fix

  • Fixed version 1.1.14
    pip install --upgrade langchain-openai==1.1.14

Fix commands are the export's own generic commands. Ojuju never runs them. Check them against your setup first.

Check your own computer: guard packages check

View this record on OSV.dev

Source

Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0

Sources & licences