- CVSS
- HIGH · 7.7v3.1CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:C/C:H/I:N/A:N
- Published
- 2026-09-14
- Weakness
- CWE-943
- Source
- nvd.nist.gov/vuln/detail/CVE-2026-55253
Description
LangChain MongoDB provides integrations between MongoDB, Atlas, LangChain, and LangGraph. Prior to langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0, MongoDBSaver.list(), MongoDBSaver.alist(), and MongoDBStore.search() incorporate filter dictionaries into MongoDB queries without recursively rejecting keys prefixed with $. An authenticated caller who controls a filter argument through HTTP query parameters, request body fields, or agent tool arguments can inject MongoDB Query Language operators such as $regex or $where. In a multi-tenant deployment that uses the filter to enforce per-user or per-tenant isolation, injected operators can bypass intended equality filtering and expose other tenants’ checkpoint or store data. Filters constructed entirely from trusted server-side values have lower practical risk. This issue is fixed in langgraph-checkpoint-mongodb 0.3.0 and langgraph-store-mongodb 0.4.0.
References
- https://github.com/langchain-ai/langchain-mongodb/commit/14a6cc39e67d23fd409cd13a9caae2c329df0a09
- https://github.com/langchain-ai/langchain-mongodb/commit/240e7ecee432ea006d9fef6ea506bfd2e009a3f4
- https://github.com/langchain-ai/langchain-mongodb/commit/5465e4d3ea0ef5c88a666a6442bd853ff4bd70e5
- https://github.com/langchain-ai/langchain-mongodb/pull/384
- https://github.com/langchain-ai/langchain-mongodb/releases/tag/libs/langgraph-checkpoint-mongodb/v0.4.0
- https://github.com/langchain-ai/langchain-mongodb/releases/tag/libs/langgraph-store-mongodb/v0.3.0
How GTK Cyber trains on this
AI security training at GTK Cyber covers the LLM and ML-pipeline vulnerability classes that vulnerabilities like CVE-2026-55253 fall into. Our hands-on courses are taught by Charles Givre and other practitioners who break and defend production AI systems.