CVE-2026-41182: medium-severity vulnerability in langchain-ai langsmith-sdk
LangSmith SDK: Streaming token events bypass output redaction
Published
E-mail alert when it lands in KEV, gets a public PoC or its score goes up.
13Vexday Risk Score
No sign of exploitation. No public exploitation artifact known so far.
ssvc Trackcvss 5.3epss 0.2%
LangSmith Client SDKs provide SDK's for interacting with the LangSmith platform. Prior to version 0.5.19 of the JavaScript SDK and version 0.7.31 of the Python SDK, the LangSmith SDK's output redaction controls (hideOutputs in JS, hide_outputs in Python) do not apply to streaming token events. When an LLM run produces streaming output, each chunk is recorded as a new_token event containing the raw token value. These events bypass the redaction pipeline entirely — prepareRunCreateOrUpdateInputs (JS) and _hide_run_outputs (Python) only process the inputs and outputs fields on a run, never the events array. As a result, applications relying on output redaction to prevent sensitive LLM output from being stored in LangSmith will still leak the full streamed content via run events. Version 0.5.19 of the JavaScript SDK and version 0.7.31 of the Python SDK fix the issue.
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
Affected products
langchain-ai · langsmith-sdkRelated CVEs — langchain-ai langsmith-sdk
In the same product, most dangerous first.
CVE-2026-40190MEDIUMLangSmith Client SDKs has Prototype Pollution in langsmith-sdk via Incomplete `__proto__` Guard in Internal lodash `set()`EPSS 0.3%CVE-2026-25528MEDIUMLangSmith Client SDK Affected by Server-Side Request Forgery via Tracing Header InjectionEPSS 0.3%CVE-2026-45134HIGHLangSmith Client SDK: Public prompt pull deserializes untrusted manifests without trust boundary warningEPSS 0.2%CVE-2026-59152MEDIUMArbitrary server-side file read in LangSmith SDK TracingMiddlewareEPSS 0.2%