LangSmith SDK Output Redaction Bypass in Streaming Tokens (0.5.18/0.7.30)
CVE-2026-41182 Published on April 23, 2026

LangSmith SDK: Streaming token events bypass output redaction
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.

NVD

Vulnerability Analysis

CVE-2026-41182 is exploitable with network access, and does not require authorization privileges or user interaction. This vulnerability is considered to have a low attack complexity. The potential impact of an exploit of this vulnerability is considered to have a small impact on confidentiality, a small impact on integrity and availability.

Attack Vector:
NETWORK
Attack Complexity:
LOW
Privileges Required:
NONE
User Interaction:
NONE
Scope:
UNCHANGED
Confidentiality Impact:
LOW
Integrity Impact:
NONE
Availability Impact:
NONE

Weakness Types

What is an Information Disclosure Vulnerability?

The product exposes sensitive information to an actor that is not explicitly authorized to have access to that information.

CVE-2026-41182 has been classified to as an Information Disclosure vulnerability or weakness.

What is a Privacy violation Vulnerability?

The product does not properly prevent a person's private, personal information from being accessed by actors who either (1) are not explicitly authorized to access the information or (2) do not have the implicit consent of the person about whom the information is collected.

CVE-2026-41182 has been classified to as a Privacy violation vulnerability or weakness.

Insertion of Sensitive Information into Log File

Information written to log files can be of a sensitive nature and give valuable guidance to an attacker or expose sensitive user information.


Affected Versions

langchain-ai langsmith-sdk: