CVE-2026-25750

Langchain Helm Charts (prior to version 0.12.71) include a URL parameter injection vulnerability in LangSmith Studio that could exfiltrate a victim’s bearer token, user ID, and workspace ID to an attacker-controlled server when an authenticated LangSmith user clicks a malicious link. Affected dep...

CVE-2026-25750 LangSmith Studio has URL Parameter Injection Vulnerability that Enables Token Theft via Malicious baseUrl

Langchain Helm Charts are Helm charts for deploying Langchain applications on Kubernetes. Prior to langchain-ai/helm version 0.12.71, a URL parameter injection vulnerability existed in LangSmith Studio that could allow unauthorized access to user accounts through stolen authentication tokens. The...

Langchain Helm Charts 注入漏洞

Langchain Helm Charts is a Kubernetes Helm chart library developed by LangChain for deploying Langchain applications. Versions of Langchain Helm Charts prior to 0.12.71 contained a injection vulnerability. This vulnerability stemmed from URL parameter injections in LangSmith Studio, which could...

PT-2026-23069

Name of the Vulnerable Software and Affected Versions Langchain Helm Charts versions prior to 0.12.71 Description Langchain Helm Charts, used for deploying Langchain applications on Kubernetes, had a flaw where a specially crafted link could lead to the theft of authentication tokens. This allowe...

CVE-2026-25528

LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. The LangSmith SDK's distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary apiurl values through the baggage header, causing the SDK to...

CVE-2026-25528

LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. The LangSmith SDK's distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary apiurl values through the baggage header, causing the SDK to...

Server-side Request Forgery (SSRF)

Overview langsmith is a Client library to connect to the LangSmith Observability and Evaluation Platform. Affected versions of this package are vulnerable to Server-side Request Forgery SSRF due to the improper validation of apiurl and apikey fields in baggage headers in RunTree.fromheaders and...

0xgasless-mcp (>=1.0.3, <=1.0.5), 4d-vector-search (>=1.0.0, <=1.0.1) +2213 more potentially affected by CVE-2026-25528 via langsmith (>=0.3.71, <=0.3.87)

langsmith NPM version =0.3.71, =1.0.3, =1.0.0, =1.11.0, =0.0.5, =0.0.1, =1.0.0, =0.0.0-dev-nicolas-fix-publishing-aurora-mcp-1750279939, =0.0.65, =1.0.6, =0.0.1, =0.0.1, =2.0.0, =2.2.0 - @adb-storage-m/mem0ai 2.3.2 and more Source cves: CVE-2026-25528 Source advisory: SNYK:JS-LANGSMITH-15253025...

0xgasless-mcp (>=1.0.3, <=1.0.5), 4d-vector-search (>=1.0.0, <=1.0.1) +2213 more potentially affected by CVE-2026-25528 via langsmith (>=0.3.71, <=0.3.87)

langsmith NPM version =0.3.71, =1.0.3, =1.0.0, =1.11.0, =0.0.5, =0.0.1, =1.0.0, =0.0.0-dev-nicolas-fix-publishing-aurora-mcp-1750279939, =0.0.65, =1.0.6, =0.0.1, =0.0.1, =2.0.0, =2.2.0 - @adb-storage-m/mem0ai 2.3.2 and more Source cves: CVE-2026-25528 Source advisory: OSV:GHSA-V34V-RQ6J-CJ6P...

GHSA-V34V-RQ6J-CJ6P LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection

Summary The LangSmith SDK's distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary apiurl values through the baggage header, causing the SDK to exfiltrate sensitive trace data to attacker-controlled endpoints. ---...

LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection

Summary The LangSmith SDK's distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary apiurl values through the baggage header, causing the SDK to exfiltrate sensitive trace data to attacker-controlled endpoints. ---...

CVE-2026-25528 LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection

LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. The LangSmith SDK's distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary apiurl values through the baggage header, causing the SDK to...

CVE-2026-25528 LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection

LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. The LangSmith SDK's distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary apiurl values through the baggage header, causing the SDK to...

CVE-2026-25528 LangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header Injection

LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. The LangSmith SDK's distributed tracing feature is vulnerable to Server-Side Request Forgery via malicious HTTP headers. An attacker can inject arbitrary apiurl values through the baggage header, causing the SDK to...

LangSmith Client SDKs 代码问题漏洞

LangSmith Client SDKs are a developer toolkit open-sourced by LangChain. Versions of LangSmith Client SDKs prior to 0.6.3 and 0.4.6 contained code vulnerabilities. These vulnerabilities stemmed from the distributed tracking feature not verifying HTTP headers, which could lead to server-side reque...

AgentSmith Flaw in LangSmith’s Prompt Hub Exposed User API Keys, Data

A CVSS 8.8 AgentSmith flaw in LangSmith's Prompt Hub exposed AI agents to data theft and LLM manipulation. Learn how malicious AI agents could steal API keys and hijack LLM responses. Fix deployed...

LangSmith Bug Could Expose OpenAI Keys and User Data via Malicious Agents

Cybersecurity researchers have disclosed a now-patched security flaw in LangChain's LangSmith platform that could be exploited to capture sensitive data, including API keys and user prompts. The vulnerability, which carries a CVSS score of 8.8 out of a maximum of 10.0, has been codenamed AgentSmi...