CVE-2026-25528VulnerabilityPublished 9 Feb 2026

CVE-2026-25528: langchain-ai langsmith-sdk · Server-Side Request Forgery (SSRF)

Affects langchain-ai langsmith-sdkSource CVE Database V5

Not known to be exploited · CVSS 5.8 Medium : upgrade to 0.6.3 when convenient.

Data as of 26 Oct 2026, 06:26 UTC

CVSS 3.1 base score

5.8Medium

How severe the flaw is on the 0–10 CVSS scale.

EPSS: 0.3% chance of exploitation in 30 days – higher than 24% of CVEsExploit Prediction Scoring System: the likelihood attackers will use this flaw soon.
Patch: Available – fixed in 0.6.3

CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:N/A:N

Attack Vector: Network
Attack Complexity: Low
Privileges Required: None
User Interaction: None
Scope: Changed
Confidentiality: Low
Integrity: None
Availability: None

Bold values are the worst case: easiest to exploit or largest impact.

Attack Vector: Network: The vulnerable component is bound to the network stack and the set of possible attackers extends beyond the other options listed, up to and including the entire Internet. Such a vulnerability is often termed 'remotely exploitable' and can be thought of as an attack being exploitable at the protocol level one or more network hops away (e.g., across one or more routers).
Attack Complexity: Low: Specialized access conditions or extenuating circumstances do not exist. An attacker can expect repeatable success against the vulnerable component.
Privileges Required: None: The attacker is unauthorized prior to attack, and therefore does not require any access to settings or files to carry out an attack.
User Interaction: None: The vulnerable system can be exploited without any interaction from any user.
Scope: Changed: An exploited vulnerability can affect resources beyond the security scope managed by the security authority of the vulnerable component. In this case, the vulnerable component and the impacted component are different and managed by different security authorities.
Confidentiality: Low: There is some loss of confidentiality. Access to some restricted information is obtained, but the attacker does not have control over what information is obtained, or the amount or kind of loss is limited. The information disclosure does not cause a direct, serious loss to the impacted component.
Integrity: None: There is no loss of integrity within the impacted component.
Availability: None: There is no impact to availability within the impacted component.

Definitions: FIRST CVSS v3.1 specification.

Exploitation evidence

Disclosed: evidence found.
CVE published 9 Feb 2026
Detectable: no evidence on record.
No public nuclei template indexed
Weaponised: no evidence on record.
No public exploit code indexed in Metasploit or Exploit-DB
Exploited in the wildExploited: no evidence on record.
Not in CISA KEV and no source reports exploitation
Observed by OffSeq MirageSeen by Mirage: no evidence on record.
No attack traffic recorded by OffSeq Mirage sensors

A missing step is not evidence of safety. Sources: cve.org (opens in a new tab), the Metasploit, Exploit-DB and nuclei-templates index as of 2026-10-26.

Disclosed: The CVE record is public on cve.org. Its publication is t = 0.
Detectable: A public nuclei template can find exposed instances, for defenders and attackers alike.
Weaponised: Public exploit code exists in Metasploit or Exploit-DB, or CISA SSVC reports a public proof of concept.
Exploited in the wild: CISA KEV lists it, CISA SSVC rates exploitation active, or a source reports attacks.
Observed by OffSeq Mirage: OffSeq Mirage honeypot sensors recorded attack traffic for this CVE, or found exposed hosts without attack traffic.

Moments are spaced evenly, not to scale; a dashed line marks a gap of six months or more. Deltas count from t = 0. Sources that give only a date (CISA KEV, Exploit-DB, or a time of exactly 00:00Z) read “same day” rather than hours. Metasploit modules carry the flaw’s disclosure date, not their release date, and nuclei templates carry no date, so both appear above but not on the timeline.

What to do

Upgrade langchain-ai langsmith-sdk to 0.6.3.

Affected software

Product	Affected	Fixed in
langchain-ailangsmith-sdk	Affected >=0.4.10 <0.6.3	Fixed in 0.6.3

AI-suggested

European organizations should immediately upgrade langsmith-sdk to at least version 0.6.3 for Python and 0.4.6 for JavaScript to ensure the vulnerability is patched. Until upgrades can be applied, organizations should implement strict network egress filtering to prevent the SDK from making outbound HTTP requests to untrusted or external endpoints, especially those not explicitly whitelisted. Monitoring and logging of outbound requests from applications using the SDK can help detect anomalous traffic indicative of exploitation attempts. Additionally, organizations should audit their use of distributed tracing and the baggage header to ensure that untrusted input is not accepted or propagated. Applying Web Application Firewall (WAF) rules to detect and block suspicious baggage header values may provide temporary mitigation. Finally, review trace data for any signs of exfiltration and conduct a security assessment of internal services exposed via tracing to identify any further risks.

Description

CVE-2026-25528 is a Server-Side Request Forgery (SSRF) vulnerability in the langchain-ai langsmith-sdk affecting versions >= 0.4.10 and < 0.6.3. The vulnerability arises from the SDK's distributed tracing feature, which accepts unvalidated api_url values injected via the baggage HTTP header. An attacker can exploit this by injecting malicious URLs, causing the SDK to send sensitive trace data to attacker-controlled endpoints. This flaw affects both the Python and JavaScript SDKs prior to versions 0.6.3 and 0.

Impact

For European organizations, this vulnerability poses a risk of sensitive trace data leakage, which may include operational metadata, internal service endpoints, or other telemetry that could aid attackers in reconnaissance or further attacks. Organizations using the langsmith-sdk for distributed tracing in internal or customer-facing applications could inadvertently expose this data to malicious actors. Although the vulnerability does not directly compromise system integrity or availability, the confidentiality breach could violate data protection regulations such as GDPR if personal or sensitive information is included in traces. This could lead to regulatory penalties and reputational damage. Additionally, the SSRF could be leveraged as a pivot point for further internal network attacks if the attacker-controlled endpoints are used to probe or exploit internal services. The medium severity rating reflects moderate risk, but the ease of exploitation without authentication increases urgency for organizations relying on these SDK versions.

CWE-918Server-Side Request Forgery (SSRF) (opens in a new tab)
Base weaknessCWE Top 25 (2025): #22OWASP Top 10 A01:2025: Broken Access Control (opens in a new tab)
The web server receives a URL or similar request from an upstream component and retrieves the contents of this URL, but it does not sufficiently ensure that the request is being sent to the expected destination.
OWASP Cheat Sheets
Server Side Request Forgery Prevention (opens in a new tab)
Unvalidated Redirects and Forwards (opens in a new tab)
Cross Site Scripting Prevention (opens in a new tab)
DOM based XSS Prevention (opens in a new tab)
Authorization (opens in a new tab)
OWASP ASVS 4.0.3
V12.6.1 (opens in a new tab)
V5.2.6 (opens in a new tab)
Attack patterns
Server Side Request Forgery (opens in a new tab)
From MITRE CWE, MITRE CAPEC and OWASP (Top 10, OpenCRE).

References

github.com/langchain-ai/langsmith-sdk/security/advisories/GHSA-v34v-rq6j-cj6p (opens in a new tab)

Community reviews

Loading reviews…

Exploitation evidence

What to do

Affected software

Description

AI analysisMachine-generated, updated 17 Feb 2026, 09:46 UTC

WeaknessesCWE-918

Technical details

References

Community reviews

Related threats