<?xml version='1.0' encoding='UTF-8'?>
<?xml-stylesheet href="/static/style.xsl" type="text/xsl"?>
<rss xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/" version="2.0">
  <channel>
    <title>Most recent entries from all</title>
    <link>https://vulnerability.circl.lu</link>
    <description>Contains only the most 10 recent entries.</description>
    <docs>http://www.rssboard.org/rss-specification</docs>
    <generator>python-feedgen</generator>
    <language>en</language>
    <lastBuildDate>Wed, 30 Sep 2026 07:57:19 +0000</lastBuildDate>
    <item>
      <title>CVE-2026-41182 — LangSmith SDK: Streaming token events bypass output redaction</title>
      <link>https://vulnerability.circl.lu/vuln/cve-2026-41182</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; langchain-ai langsmith-sdk&lt;/p&gt;
&lt;p&gt;LangSmith Client SDKs provide SDK&amp;#39;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&amp;#39;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.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; langchain-ai langsmith-sdk&lt;/p&gt;
&lt;p&gt;LangSmith Client SDKs provide SDK&amp;#39;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&amp;#39;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.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://vulnerability.circl.lu/vuln/cve-2026-41182</guid>
    </item>
    <item>
      <title>GHSA-rr7j-v2q5-chgv — LangSmith SDK: Streaming token events bypass output redaction</title>
      <link>https://vulnerability.circl.lu/vuln/ghsa-rr7j-v2q5-chgv</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; npm: langsmith, PyPI: langsmith&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;The LangSmith SDK&amp;#39;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.&lt;/p&gt;
&lt;p&gt;## Details&lt;/p&gt;
&lt;p&gt;**Both JS and Python SDKs are affected.** The same pattern exists in both:&lt;/p&gt;
&lt;p&gt;- **JS SDK**: `traceable.ts:997-1003` and `traceable.ts:1044-1050`
- **Python SDK**: `run_helpers.py:1924` and `run_helpers.py:1996`&lt;/p&gt;
&lt;p&gt;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`.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; npm: langsmith, PyPI: langsmith&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;The LangSmith SDK&amp;#39;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.&lt;/p&gt;
&lt;p&gt;## Details&lt;/p&gt;
&lt;p&gt;**Both JS and Python SDKs are affected.** The same pattern exists in both:&lt;/p&gt;
&lt;p&gt;- **JS SDK**: `traceable.ts:997-1003` and `traceable.ts:1044-1050`
- **Python SDK**: `run_helpers.py:1924` and `run_helpers.py:1996`&lt;/p&gt;
&lt;p&gt;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`.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://vulnerability.circl.lu/vuln/ghsa-rr7j-v2q5-chgv</guid>
    </item>
    <item>
      <title>PYSEC-2026-2583 — LangSmith SDK: Streaming token events bypass output redaction</title>
      <link>https://vulnerability.circl.lu/vuln/pysec-2026-2583</link>
      <description>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: langsmith&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;The LangSmith SDK&amp;#39;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.&lt;/p&gt;
&lt;p&gt;## Details&lt;/p&gt;
&lt;p&gt;**Both JS and Python SDKs are affected.** The same pattern exists in both:&lt;/p&gt;
&lt;p&gt;- **JS SDK**: `traceable.ts:997-1003` and `traceable.ts:1044-1050`
- **Python SDK**: `run_helpers.py:1924` and `run_helpers.py:1996`&lt;/p&gt;
&lt;p&gt;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`.&lt;/p&gt;</description>
      <content:encoded>&lt;p&gt;&lt;strong&gt;Affected:&lt;/strong&gt; PyPI: langsmith&lt;/p&gt;
&lt;p&gt;## Summary&lt;/p&gt;
&lt;p&gt;The LangSmith SDK&amp;#39;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.&lt;/p&gt;
&lt;p&gt;## Details&lt;/p&gt;
&lt;p&gt;**Both JS and Python SDKs are affected.** The same pattern exists in both:&lt;/p&gt;
&lt;p&gt;- **JS SDK**: `traceable.ts:997-1003` and `traceable.ts:1044-1050`
- **Python SDK**: `run_helpers.py:1924` and `run_helpers.py:1996`&lt;/p&gt;
&lt;p&gt;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`.&lt;/p&gt;</content:encoded>
      <guid isPermaLink="false">https://vulnerability.circl.lu/vuln/pysec-2026-2583</guid>
    </item>
  </channel>
</rss>
