Skip to content
Fencer Vulns
medium 5.3

CVE-2026-41182 json

LangSmith SDK: Streaming token events bypass output redaction

published 2026-04-16 6 mo ago modified 2026-10-26 13 d ago also EUVD-2026-25152 , GHSA-rr7j-v2q5-chgv , PYSEC-2026-2583

cvss
5.3
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.2%
EPSS 0.2% chance of exploitation in 30 days, percentile 11%
public exploits
0
none known

Summary

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.

Patch / fix

  • npm langsmith 0.5.19
  • pypi langsmith 0.7.31
  • langchain langsmith 0.5.19, 0.7.31
  • python-langsmith openSUSE Tumbleweed 0.10.3-1.1

opensuse advisories openSUSE-SU-2026:11284-1

CISA SSVC

Exploitation
none
Automatable
yes
Technical impact
partial
Assessed
6 mo ago

Exploit prediction

0.21% chance of exploitation in the next 30 days, higher than 11% of all scored CVEs (FIRST EPSS, 2026-11-08).

CVSS scores

assigned by version score vector
CNA 3.1 5.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
GitHub 3.1 5.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
OSV 3.1 5.3 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N

Affected packages

ecosystem package affected fixed in
npm langsmith
<0.5.19
0.5.19
pypi langsmith
<0.7.31
0.7.31

Affected products

  • langchain-ai langsmith-sdk

Classification

Weakness
  • CWE-200 Exposure of Sensitive Information to an Unauthorized Actor
  • CWE-359 Exposure of Private Personal Information to an Unauthorized Actor
  • CWE-532 Insertion of Sensitive Information into Log File

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.

CPEs and fixed versions use Anchore's correction of NVD's data: Added CPE configurations because not yet analyzed by NVD.