INCIDENT MAP

Browse / Sensitive Data Disclosure / CVE-2026-41182

LangSmith SDK: Streaming token events bypass output redaction

CVE-2026-41182 · 2026-04-16 moderate

Class
Sensitive Data Disclosure (filed by a model that read the advisory)
Technique
Information exposure
Affected
langsmith (PyPI)
CVSS
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
EPSS
0.2% chance of exploitation in 30 days

How it works, in short

Streamed token events are recorded as raw values and skip the output redaction applied to run inputs and outputs, so sensitive model output is still stored. (Our summary, written by a model. The source text is below.)

Details

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:

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.

References

Source: GitHub Advisory Database, used under CC BY 4.0.