CVE-2026-44843
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedLangChain is a framework for building agents and LLM-powered applications. Prior to 0.3.85 and 1.3.3, LangChain contains older runtime code paths that deserialize run inputs, run outputs, or other application-controlled payloads using overly broad object allowlists. These paths may call load() with allowed_objects="all". This does not enable arbitrary Python object deserialization, but it does allow any trusted LangChain-serializable object to be revived, which is broader than these runtime paths require. As a result, attacker-supplied LangChain serialized constructor dictionaries may cause trusted runtime paths to instantiate classes with untrusted constructor arguments. This vulnerability is fixed in 0.3.85 and 1.3.3.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · high confidenceLangChain's runtime code paths deserialize run inputs, outputs, or application-controlled payloads using overly broad object allowlists (allowed_objects='all'). This allows attacker-supplied LangChain-serialized constructor dictionaries to instantiate classes with untrusted constructor arguments, leading to potential code execution via trusted serializable objects.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.
NVD · CPE data< 0.3.85>= 1.0.0, < 1.3.3CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- High
- Integrity
- Low
- Availability
- None
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:L/A:N
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Verify LangChain is installedRun `pip show langchain` or `pip list | grep -i langchain` to confirm the package is present in your environmentAffected if If LangChain is not installed, this CVE does not apply
-
Identify installed LangChain versionRun `pip show langchain` and note the version number in the Version field (e.g., 0.3.80 or 1.2.0)Affected if If no version is returned, the vulnerability status cannot be determined from version alone
-
Compare version against affected rangesCheck if your version is in an affected range: version < 0.3.85 (for 0.x branch) OR version >= 1.0.0 and < 1.3.3 (for 1.x branch)Affected if You are affected if your installed version falls into either of these ranges: < 0.3.85 OR (>= 1.0.0 AND < 1.3.3)
-
Audit code for deserialization with allowed_objects='all'Search your codebase for patterns like `load()` or `BaseSerialized.from_bytes()` called with `allowed_objects='all'` parameter, which enables the vulnerable deserialization pathAffected if Code using load() with allowed_objects='all' on untrusted input is vulnerable regardless of version
You are affected if LangChain is installed with a version less than 0.3.85 (0.x branch) or between 1.0.0 and 1.3.3 (1.x branch), and your code uses the vulnerable deserialization patterns.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
dbcve · scoped0.3.851.3.3
Upgrade LangChain to version 0.3.85 or 1.3.3 or later to receive the patched deserialization allowlist restrictions.
Upgrade to LangChain 0.3.85 (for 0.x users) or 1.3.3 (for 1.x users)
- Identify your current LangChain version by running 'pip show langchain' or checking your dependency files
- For LangChain 0.x users: Upgrade to version 0.3.85 or later by running 'pip install langchain>=0.3.85'
- For LangChain 1.x users: Upgrade to version 1.3.3 or later by running 'pip install langchain>=1.3.3'
- Verify the upgrade was successful by running 'pip show langchain' and confirming the installed version
- Test your application to ensure functionality remains intact after the upgrade
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation2.0 h
- Implementation2.0 h
- Testing4.0 h
- Review / QA2.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $2,752.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-44843 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-44843 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data