angchain-openai: Image token counting SSRF protection can be bypassed via DNS rebinding
Key facts
- Attack vector
- Network
- Privileges required
- None
- User interaction
- Required
- Attack complexity
- High
- Impact type
- Information disclosure
- Confidentiality · integrity · availability
- Low · None · None
- Fix status
- Partial Red Hat: 5 without a fix
Attack profile from CVSS 3.1 · CNA. Fix status from CNA, GitHub and Red Hat. Impact type from CWE-918 and the CVSS impact.
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.
Why it matters now
SSVC decision points
CISA ADP · SSVC 2.0.3
- Exploitation
- None
- Automatable
- No
- Technical impact
- Partial
The decision (Track, Attend, Act) also depends on your mission and well-being impact; see CISA's SSVC guide.
Affected products
| Vendor | Product | Affected versions | Fixed in | Status | Source |
|---|---|---|---|---|---|
| langchain-ai | langchain-openai | before 1.1.14 | 1.1.14 | Patch available | CNA |
| — | langchain-openai (PyPI) | before 1.1.14 | 1.1.14 | Patch available | GHSA-r7w7-9xr2-qq2r |
- langchain-openai Vendorlangchain-ai Affected before 1.1.14 Fixed in 1.1.14 Patch available CNA
- langchain-openai (PyPI) Vendor— Affected before 1.1.14 Fixed in 1.1.14 Patch available GHSA-r7w7-9xr2-qq2r
CPE configurations NVD · 1
| CPE | Versions | Role | Vendor |
|---|---|---|---|
| cpe:2.3:a:langchain:langchain-openai:*:*:*:*:*:*:*:* | before 1.1.14 | Vulnerable | langchain-ai |
- cpe:2.3:a:langchain:langchain-openai:*:*:*:*:*:*:*:* Versions before 1.1.14 Vulnerable ·langchain-ai
Remediation
- Fix · CNA langchain-openai (langchain-ai) Fixed in 1.1.14
- Fix · GHSA-r7w7-9xr2-qq2r langchain-openai (PyPI) Fixed in 1.1.14 Advisory →
Vendor assessments
Red Hat
Red Hat rating: Low. Red Hat's page for this CVE →
| Product | Status | Plan or fix |
|---|---|---|
| Migration Toolkit for Applications 8 | Affected | No fix yet: Fix deferred |
| OpenShift Lightspeed | Affected | No fix yet: Fix deferred |
| Red Hat Ansible Automation Platform 2 | Affected | No fix yet: Fix deferred |
| Red Hat Enterprise Linux AI (RHEL AI) 3 | Affected | No fix yet: Fix deferred |
| Red Hat OpenShift AI (RHOAI) | Affected | No fix yet: Fix deferred |
Timeline
- 2026-10-02 Threatist record created from CVE-2026-41488
- 2026-10-03 Alias added: GHSA-r7w7-9xr2-qq2r
References
Sources
- CVE-2026-41488 · CVE Program
- CVE-2026-41488 · NVD
- FIRST EPSS
- GHSA-r7w7-9xr2-qq2r · GitHub Advisory Database · CC BY 4.0
- CVE-2026-41488 · Red Hat security data · CC BY 4.0
This product uses the NVD API but is not endorsed or certified by the NVD. Sources and licences