Trace-data exfiltration via injected replica URL
Published Feb 9, 2026 · Updated Feb 9, 2026
SSRF in LangChain LangSmith SDK tracing allows remote attackers to exfiltrate sensitive trace data through a crafted baggage header. RunTree.from_headers() and RunTree.fromHeaders() accept unvalidated api_url values in replica configurations, and post() and patch() send run data to every injected URL. Exposure requires an application to pass untrusted HTTP headers into distributed tracing or TracingMiddleware; resulting requests can disclose prompts, completions, and metadata.
Summary
What happened
SSRF in LangChain LangSmith SDK tracing allows remote attackers to exfiltrate sensitive trace data through a crafted baggage header. RunTree.from_headers() and RunTree.fromHeaders() accept unvalidated api_url values in replica configurations, and post() and patch() send run data to every injected URL. Exposure requires an application to pass untrusted HTTP headers into distributed tracing or TracingMiddleware; resulting requests can disclose prompts, completions, and metadata.
The record
- CVE
- CVE-2026-25528
- Published
- Feb 9, 2026
- Updated
- Feb 9, 2026
- Vendor
- LangChain
- Product
- LangSmith SDK
- Classifications
- CWE-918, T1190
- Attack vector
- network
- Privileges
- unauthenticated
Timeline
How it unfolded
- Feb 9, 2026CVE publishedPublication date reported by the CVE source.
- Feb 9, 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=>= 0.4.10, <0.6.3
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
- Malicious LangSmith replica baggage header exampleproof 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