{"id":"CVE-2026-48121","aliases":["EUVD-2026-52793","GHSA-98xf-r82g-9mhx"],"status":"published","title":"@langchain/langgraph-checkpoint-mongodb: NoSQL parameter injection in MongoDBSaver allows cross-tenant state access","description":"@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1.","severity":{"version":"3.1","score":6.7,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-09","score":0.00313,"percentile":0.24346,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":true,"fix_available":true},"cwes":["CWE-943"],"published":"2026-06-12T15:05:32Z","modified":"2026-10-28T02:30:49Z","exploits":[{"source":"pocgithub","id":"decker757/cs440-langgraph-nosql-demo","title":"decker757/cs440-langgraph-nosql-demo","date":"2026-09-30","url":"https://github.com/decker757/cs440-langgraph-nosql-demo"}],"fixes":[{"ecosystem":"npm","package":"@langchain/langgraph-checkpoint-mongodb","fixed_in":["1.3.1"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"npm","package":"@langchain/langgraph-checkpoint-mongodb","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"last_affected":"1.3.0"},{"fixed":"1.3.1"}]}]},{"source":"osv","ecosystem":"npm","package":"@langchain/langgraph-checkpoint-mongodb","ranges":[{"type":"SEMVER","events":[{"introduced":"0"},{"fixed":"1.3.1"}]}]}],"products":[{"vendor":"langchain-ai","product":"langgraphjs"}],"references":[{"url":"https://github.com/langchain-ai/langgraphjs/security/advisories/GHSA-98xf-r82g-9mhx","tags":["x_refsource_CONFIRM","advisory","web"]},{"url":"https://github.com/langchain-ai/langgraphjs/issues/2351","tags":["x_refsource_MISC","report","web"]},{"url":"https://github.com/langchain-ai/langgraphjs/commit/284226c7ca164b3c81fe2d9e32b10f1fc6b99a3c","tags":["x_refsource_MISC","fix","web"]},{"url":"https://github.com/langchain-ai/langgraphjs/pull/2397","tags":["web"]},{"url":"https://github.com/advisories/GHSA-98xf-r82g-9mhx"},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/48xxx/CVE-2026-48121.json","tags":["advisory"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-48121","tags":["advisory"]},{"url":"https://github.com/langchain-ai/langgraphjs","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2026-48121","title":"@langchain/langgraph-checkpoint-mongodb: NoSQL parameter injection in MongoDBSaver allows cross-tenant state access","description":"@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1.","status":"published","published":"2026-08-04T16:49:57.68Z","modified":"2026-08-04T19:51:50.111Z","cvss":[{"version":"3.1","score":6.7,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N","level":"medium","assessor":"cna"}],"cwes":["CWE-943"],"updated_at":"2026-11-02T13:50:38.739766Z"}],"euvd":[{"id":"EUVD-2026-52793","description":"@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1.","status":"published","published":"2026-08-04T16:49:57Z","modified":"2026-08-04T19:51:50Z","cvss":[{"version":"3.1","score":6.7,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N","level":"medium"}],"updated_at":"2026-11-02T18:02:22.516769Z"}],"ghsa":[{"id":"GHSA-98xf-r82g-9mhx","title":"LangGraph has NoSQL parameter injection in MongoDBSaver, allowing cross-tenant state access","description":"## Summary\n\nA NoSQL injection vulnerability existed in `MongoDBSaver` where checkpoint identifier fields from `config.configurable` were used in MongoDB queries without strict type enforcement. In vulnerable versions, attacker-controlled object payloads (for example MongoDB operators like `$gt` and `$ne`) could be interpreted as query operators instead of literal identifier values.\n\nThis could bypass intended thread scoping and return checkpoints from other tenants.\n\n## Attack surface\n\nThe vulnerable path was in `MongoDBSaver.getTuple()`, where `thread_id`, `checkpoint_ns`, and `checkpoint_id` were used in MongoDB `find()` queries. The same unvalidated values were then reused to fetch pending writes.\n\nApplications were exposed when untrusted input was forwarded into `config.configurable` (for example, directly from request bodies or query parameters) without string coercion or schema validation.\n\n## Who is affected?\n\nApplications are vulnerable if they:\n\n- Use `@langchain/langgraph-checkpoint-mongodb` with multi-tenant or user-isolated thread models.\n- Accept user-controlled values for `thread_id`, `checkpoint_ns`, or `checkpoint_id`.\n- Pass those values into `app.invoke()`, `app.stream()`, or direct saver methods without validation.\n\nApplications are generally not vulnerable if they:\n\n- Use server-issued identifiers only.\n- Source `thread_id` from trusted URL params that remain strings.\n- Enforce schema validation that rejects non-string identifier fields.\n\n## Impact\n\nAn attacker with control over configurable checkpoint identifiers could read checkpoint data outside their authorized thread boundary.\n\nPotentially exposed data includes:\n\n- Checkpoint state\n- Metadata\n- Pending writes\n\nThis is a confidentiality issue with cross-tenant data disclosure risk.\n\n## Exploit example\n\nAn attacker-controlled request can inject MongoDB operators:\n\n```ts\ngraph = new StateGraph(...)\n  .compile({\n    checkpointer: new MongoDBSaver()\n  });\n\ngraph.invoke(..., {\n  configurable: {  \n    \"thread_id\": { \"$gt\": \"\" },\n    \"checkpoint_ns\": { \"$ne\": null }\n  }\n});\n```\n\nIf this payload is forwarded into `config.configurable`, the resulting query may match checkpoints outside the intended tenant/thread scope.\n\n## Security hardening changes\n\nVersion `1.3.1` hardens `@langchain/langgraph-checkpoint-mongodb` by adding runtime validation for configurable checkpoint identifiers and rejecting invalid values before MongoDB query/write paths execute.\n\nThe patch also includes regression tests covering object/operator payloads across affected methods.\n\n## Migration guide\n\nUpgrade to `@langchain/langgraph-checkpoint-mongodb@1.3.1` or later.\n\nNo API migration is required for valid callers. However, applications that currently pass non-string identifier values in `config.configurable` will now receive explicit errors and should normalize/validate inputs.\n\nAs defense in depth, validate identifier fields at API boundaries and avoid passing raw client objects into graph config.\n\n## Resources\n\n- Issue: https://github.com/langchain-ai/langgraphjs/issues/2351\n- Fix PR: https://github.com/langchain-ai/langgraphjs/pull/2397","status":"published","published":"2026-06-12T15:05:32Z","modified":"2026-06-12T15:05:32Z","cvss":[{"version":"3.1","score":6.7,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N","level":"medium"}],"cwes":["CWE-943"],"updated_at":"2026-11-02T14:40:26.12116Z"}],"nvd":[{"id":"CVE-2026-48121","description":"@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1.","status":"published","published":"2026-08-04T17:16:55.267Z","modified":"2026-10-24T16:10:00.153Z","cvss":[{"version":"3.1","score":6.7,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N","level":"medium","assessor":"secondary"}],"cwes":["CWE-943"],"updated_at":"2026-11-02T14:12:34.643497Z"}],"osv":[{"id":"CVE-2026-48121","title":"@langchain/langgraph-checkpoint-mongodb: NoSQL parameter injection in MongoDBSaver allows cross-tenant state access","description":"@langchain/langgraph-checkpoint-mongodb provides a LangGraph.js CheckpointSaver implementation that uses MongoDB for storage. Versions 1.3.0 and below are vulnerable to NoSQL injection: checkpoint identifiers (thread_id, checkpoint_ns, checkpoint_id) from config.configurable are passed into MongoDB find() queries in MongoDBSaver.getTuple() without type enforcement. If an attacker supplies an object payload (such as MongoDB operators $gt or $ne) instead of a string, it can be interpreted as a query operator, bypassing thread scoping and leaking checkpoints, including pending writes, across tenants. Applications are at risk if they forward untrusted input into config.configurable without coercing it to strings or validating it against a schema, particularly in multi-tenant or user-isolated setups. Apps that only use server-issued, string-typed identifiers with schema validation rejecting non-string fields are not affected. This issue has been fixed in version 1.3.1.","status":"published","published":"2026-08-04T16:49:57.68Z","modified":"2026-10-28T02:30:49.144000855Z","cvss":[{"version":"3.1","score":6.7,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N","level":"medium"}],"cwes":["CWE-943"],"updated_at":"2026-11-02T15:45:06.701612Z"},{"id":"GHSA-98xf-r82g-9mhx","title":"LangGraph has NoSQL parameter injection in MongoDBSaver, allowing cross-tenant state access","description":"## Summary\n\nA NoSQL injection vulnerability existed in `MongoDBSaver` where checkpoint identifier fields from `config.configurable` were used in MongoDB queries without strict type enforcement. In vulnerable versions, attacker-controlled object payloads (for example MongoDB operators like `$gt` and `$ne`) could be interpreted as query operators instead of literal identifier values.\n\nThis could bypass intended thread scoping and return checkpoints from other tenants.\n\n## Attack surface\n\nThe vulnerable path was in `MongoDBSaver.getTuple()`, where `thread_id`, `checkpoint_ns`, and `checkpoint_id` were used in MongoDB `find()` queries. The same unvalidated values were then reused to fetch pending writes.\n\nApplications were exposed when untrusted input was forwarded into `config.configurable` (for example, directly from request bodies or query parameters) without string coercion or schema validation.\n\n## Who is affected?\n\nApplications are vulnerable if they:\n\n- Use `@langchain/langgraph-checkpoint-mongodb` with multi-tenant or user-isolated thread models.\n- Accept user-controlled values for `thread_id`, `checkpoint_ns`, or `checkpoint_id`.\n- Pass those values into `app.invoke()`, `app.stream()`, or direct saver methods without validation.\n\nApplications are generally not vulnerable if they:\n\n- Use server-issued identifiers only.\n- Source `thread_id` from trusted URL params that remain strings.\n- Enforce schema validation that rejects non-string identifier fields.\n\n## Impact\n\nAn attacker with control over configurable checkpoint identifiers could read checkpoint data outside their authorized thread boundary.\n\nPotentially exposed data includes:\n\n- Checkpoint state\n- Metadata\n- Pending writes\n\nThis is a confidentiality issue with cross-tenant data disclosure risk.\n\n## Exploit example\n\nAn attacker-controlled request can inject MongoDB operators:\n\n```ts\ngraph = new StateGraph(...)\n  .compile({\n    checkpointer: new MongoDBSaver()\n  });\n\ngraph.invoke(..., {\n  configurable: {  \n    \"thread_id\": { \"$gt\": \"\" },\n    \"checkpoint_ns\": { \"$ne\": null }\n  }\n});\n```\n\nIf this payload is forwarded into `config.configurable`, the resulting query may match checkpoints outside the intended tenant/thread scope.\n\n## Security hardening changes\n\nVersion `1.3.1` hardens `@langchain/langgraph-checkpoint-mongodb` by adding runtime validation for configurable checkpoint identifiers and rejecting invalid values before MongoDB query/write paths execute.\n\nThe patch also includes regression tests covering object/operator payloads across affected methods.\n\n## Migration guide\n\nUpgrade to `@langchain/langgraph-checkpoint-mongodb@1.3.1` or later.\n\nNo API migration is required for valid callers. However, applications that currently pass non-string identifier values in `config.configurable` will now receive explicit errors and should normalize/validate inputs.\n\nAs defense in depth, validate identifier fields at API boundaries and avoid passing raw client objects into graph config.\n\n## Resources\n\n- Issue: https://github.com/langchain-ai/langgraphjs/issues/2351\n- Fix PR: https://github.com/langchain-ai/langgraphjs/pull/2397","status":"published","published":"2026-06-12T15:05:32Z","modified":"2026-09-10T03:50:49.235778397Z","cvss":[{"version":"3.1","score":6.7,"vector":"CVSS:3.1/AV:A/AC:L/PR:L/UI:R/S:U/C:H/I:H/A:N","level":"medium"}],"cwes":["CWE-943"],"updated_at":"2026-11-02T15:46:43.524801Z"}]}}