Description
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.
Affected products
| Vendor | Product | Affected | Fixed |
|---|---|---|---|
| langchain-ai | langchain-openai | < 1.1.14 | — |
Affected packages
| Ecosystem | Package | Affected | Fixed | Record |
|---|---|---|---|---|
| PyPI | langchain-openai | < 1.1.14 | 1.1.14 | GHSA-r7w7-9xr2-qq2r |
Advisories 2
- WID-SEC-2026-3046 IBM Concert: Mehrere Schwachstellen BSI CERT-Bund (WID) · Nov 10, 2026
- WID-SEC-2026-1275 LangChain (openai, text-splitters): Mehrere Schwachstellen ermöglichen Offenlegung von Informationen und SSRF-Umgehung BSI CERT-Bund (WID) · Jun 28, 2026