GHSA-rr7j-v2q5-chgv
## 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`.
Properties
- ghsa_id
- GHSA-rr7j-v2q5-chgv
- severity
- medium
- summary
- LangSmith SDK: Streaming token events bypass output redaction
- cvss_score
- 5.3
- cve_id
- GHSA-rr7j-v2q5-chgv
- cvss_vector
- CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:N/A:N
- is_ghsa_only
- true
- ghsa_published
- 2026-04-16T01:20:37Z
- source_url
- https://github.com/advisories/GHSA-rr7j-v2q5-chgv
- ghsa_updated
- 2026-04-16T01:20:38Z
Related Entities (8)
AFFECTS (2)
HAS_WEAKNESS (3)
REPORTED_BY (1)
VULNERABLE_TO (2)
Explore deeper with Ninja Signal's threat intelligence graph