HomeCVE Intelligence › CVE-2026-44843
CVSS 8.2 HIGH Vulnerability

CVE-2026-44843: LangChain vulnerable to unsafe deserialization of attacker-controlled objects through ove…

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"…

8.2CVSS Score
HIGHSeverity
NOCISA KEV
VulnerabilityImpact Type

📋 Vulnerability Details

CVE IDCVE-2026-44843
Vendorpip
Affected Productlangchain-core
Vulnerability TypeVulnerability
CVSS Score8.2 (HIGH)
Actively Exploited❌ No known exploitation
Patch StatusSee Vendor Advisory →
Reported ByCYBERDUDEBIVASH SENTINEL APEX Intelligence (via github_advisories)

🔬 Technical Analysis

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. Applications are exposed only when all of the following are true: 1. The application accepts untrusted structured input, such as JSON, from a user or network request. 2. The application does not validate or canonicali

📚 Advisory References

⚡ DETECTION RULES AVAILABLE

Get CVE-2026-44843 Detection Pack

Sigma rules, YARA signatures, IOC table, and SIEM queries for Splunk, Elastic, Sentinel, and Chronicle — deployable in 5 minutes.

✓ Sigma Rules ✓ YARA Pack ✓ IOC Table ✓ SIEM Queries
🛡️ Get Detection Pack → 🔌 Access via API →

🔗 Related Intelligence