Free AI Safety Workshop — in collaboration with explainx.aiSave your seat
AgentbeamBeta
AI agent vulnerability · LangSmith SDK

CVE-2026-41182: LangSmith SDK: Streaming token events bypass output redaction

mediumCVSS 3.1 5.3GHSA-rr7j-v2q5-chgv

Summary The LangSmith SDK's output redaction controls (hideOutputs in JS, hideoutputs in Python) do not apply to streaming token events. When an LLM run produces streaming output, each chunk is recorded as a newtoken event containing the raw token value.

Published Apr 16, 2026 · Updated Apr 24, 2026

Affected packages

langsmith

Ecosystem
npm
Affected
<= 0.5.18
Fixed in
0.5.19
Check
npm ls langsmith

langsmith

Ecosystem
PyPI
Affected
<= 0.7.30
Fixed in
0.7.31
Check
pip show langsmith

Advisory details

From the GitHub Advisory Database (CC BY 4.0).

Summary

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.

Details

Both JS and Python SDKs are affected. The same pattern exists in both:

  • JS SDK: traceable.ts:997-1003 and traceable.ts:1044-1050
  • Python SDK: run_helpers.py:1924 and run_helpers.py:1996

In both SDKs, new_token events with raw kwargs.token values are added during streaming, and the redaction pipeline (hideOutputs in JS, hide_outputs in Python) only processes inputs/outputs — never events.

Credited to ryu7eroo.

References

How this page is made: the data panel comes from the GitHub Advisory Database, CISA’s KEV catalog, the NVD and FIRST EPSS, and updates twice a day. No analysis has been written for this entry yet. Methodology

More LangSmith SDK vulnerabilities

All LangSmith SDK entries