Blind SSRF via unvalidated image token counting
Published Feb 10, 2026 · Updated Feb 10, 2026
SSRF in LangChain before 1.2.11 allows remote attackers to make application servers request arbitrary URLs via crafted image URLs. ChatOpenAI.get_num_tokens_from_messages() passes non-low-detail image_url values to _url_to_size(), which calls httpx.get() without validating the destination. Reachability requires an application to token-count attacker-controlled vision messages; the blind requests can access internal services or consume limited resources, but responses are not returned.
Summary
What happened
SSRF in LangChain before 1.2.11 allows remote attackers to make application servers request arbitrary URLs via crafted image URLs. ChatOpenAI.get_num_tokens_from_messages() passes non-low-detail image_url values to _url_to_size(), which calls httpx.get() without validating the destination. Reachability requires an application to token-count attacker-controlled vision messages; the blind requests can access internal services or consume limited resources, but responses are not returned.
The record
- CVE
- CVE-2026-26013
- Published
- Feb 10, 2026
- Updated
- Feb 10, 2026
- Vendor
- LangChain
- Product
- LangChain
- Classifications
- CWE-918, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Feb 10, 2026CVE publishedPublication date reported by the CVE source.
- Feb 10, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 1.2.11
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo