langchain-openai
Affected
- introduced
0, fixed1.1.14(ecosystem)
Fixed versions
1.1.14
Fix
- Fixed version
1.1.14pip install --upgrade langchain-openai==1.1.14
Advisory
Also known as: CVE-2026-41488, PYSEC-2026-76
langchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding
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 < 1.1.14Patched 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:
This fix was released in langchain-openai 1.1.14.
Low Basis: The source's own band: LOW
0, fixed 1.1.14 (ecosystem)1.1.14
1.1.14pip install --upgrade langchain-openai==1.1.14Fix 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
Source: GitHub Advisory Database (reviewed advisories) · CC BY 4.0