SSRF via untrusted public prompt deserialization
Published May 27, 2026 · Updated May 27, 2026
Deserialization in LangSmith SDK before Python 0.8.0 and JS/TS 0.6.0 allows remote attackers to redirect application requests. The prompt pull methods deserialize public owner/name manifests as executable configuration, instantiating LangChain objects with attacker-controlled constructor arguments. Exploitation requires an application to pull an untrusted public prompt and use it without validation; model endpoint settings can expose prompts, context, or credentials.
Summary
What happened
Deserialization in LangSmith SDK before Python 0.8.0 and JS/TS 0.6.0 allows remote attackers to redirect application requests. The prompt pull methods deserialize public owner/name manifests as executable configuration, instantiating LangChain objects with attacker-controlled constructor arguments. Exploitation requires an application to pull an untrusted public prompt and use it without validation; model endpoint settings can expose prompts, context, or credentials.
The record
- CVE
- CVE-2026-45134
- Published
- May 27, 2026
- Updated
- May 27, 2026
- Vendor
- LangChain
- Product
- LangSmith SDK
- Classifications
- Unavailable
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- May 27, 2026CVE publishedPublication date reported by the CVE source.
- May 27, 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=< 0.6.0
- Affected versionversion=< 0.8.0
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
No sourced classifications are available.
Public exploit references
- LangGhost proof of conceptproof of concept · demonstrated
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