CVE-2025-68664
LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs
Public exploit available. Not confirmed exploited in the wild yet. A vendor fix is available.
What to do
The vendor has published a fix. Version details are below where the sources state them.
What it is
From the CVE record
LangChain is a framework for building agents and LLM-powered applications. Prior to versions 0.3.81 and 1.2.5, a serialization injection vulnerability exists in LangChain's dumps() and dumpd() functions. The functions do not escape dictionaries with 'lc' keys when serializing free-form dictionaries. The 'lc' key is used internally by LangChain to mark serialized objects. When user-controlled data contains this key structure, it is treated as a legitimate LangChain object during deserialization rather than plain user data. This issue has been patched in versions 0.3.81 and 1.2.5.
In plain language
No plain-language summary for this CVE yet.
Exploitation
Where each signal puts this CVE on the scale from published to confirmed exploited.
- CISA KEV
Not in the catalog. CISA has not confirmed exploitation.
- Public exploits
1 source with a proof of concept or module.
Exploit links, PoCs and Metasploit modules after sign-in- EPSS
43% chance of exploitation activity in the next 30 days, which ranks it in the 99th percentile of scored CVEs.
Exploit Prediction Scoring System, FIRST.org. A probability, not a confirmation.
Lifecycle
The patch came 52 days before any public exploit.
- EPSS band changelow → moderate
- Public exploit / PoCsource: github-poc
- Patch availablerecord updated
- Publishedweakness classified, att&ck mapped
Affected products
Technical detail
CVSS 3.1 vector
Open in the CVSS calculatorCVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N
Scored 9.3 by NVD.
How it is reached
- Attack Vector NetworkExploitable remotely over the network without any special conditions
- Attack Complexity LowNo special conditions — the attack can be reliably reproduced
- Privileges Required NoneNo authentication required — anyone can exploit this
- User Interaction NoneNo user interaction needed — fully automated exploitation
Scope
- Scope ChangedThe exploit can affect other components (e.g. sandbox escape, host compromise from VM)
Impact if exploited
- Confidentiality HighTotal information disclosure — all data in the component is compromised
- Integrity LowData modification is possible but limited in scope or consequence
- Availability NoneNo availability impact
Weaknesses
ATT&CK techniques
Mapped from the weaknesses above (CWE to ATT&CK), not observed in attacks.
Sources
References in the record
- github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cm
- github.com/langchain-ai/langchain/pull/34455
- github.com/langchain-ai/langchain/pull/34458
And 6 more references. See all after sign-in
In the news
Watch the software you run.
My Stack ranks new CVEs for your products by real-world exploitation, so the next serious one reaches you without reading every advisory.
We'll flag the next CVE, public exploit or patch for Langchain, not every advisory. This one: public exploit.
A free account adds
- The full version matrix and every affected product
- Exploit links, proofs of concept and Metasploit modules
- Email alerts for the products you watch
- The same data over REST API, MCP and CLI