{"id":"CVE-2025-68664","aliases":["GHSA-c67j-w6g6-q2cm","PYSEC-2026-373"],"title":"LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs","summary":"LangChain serialization injection vulnerability enables secret extraction in dumps/loads APIs","severity":"critical","cvss":9.3,"cvssVector":"CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:L/A:N","vendor":"langchain-core","product":"langchain-core","ecosystem":"pip","affected":["langchain-core >= 1.0.0, < 1.2.5","langchain-core < 0.3.81"],"patched":["langchain-core 1.2.5","langchain-core 0.3.81"],"published":"2025-12-23","updated":"2026-10-27","sourceUpdated":"2026-10-27T17:00:03.967428014Z","source":"OSV","sourceUrl":"https://osv.dev/vulnerability/GHSA-c67j-w6g6-q2cm","references":[{"url":"https://github.com/langchain-ai/langchain/security/advisories/GHSA-c67j-w6g6-q2cm"},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2025-68664"},{"url":"https://github.com/langchain-ai/langchain/pull/34455"},{"url":"https://github.com/langchain-ai/langchain/pull/34458"},{"url":"https://github.com/langchain-ai/langchain/commit/5ec0fa69de31bbe3d76e4cf9cd65a6accb8466c8"},{"url":"https://github.com/langchain-ai/langchain/commit/d9ec4c5cc78960abd37da79b0250f5642e6f0ce6"},{"url":"https://github.com/langchain-ai/langchain"},{"url":"https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D0.3.81"},{"url":"https://github.com/langchain-ai/langchain/releases/tag/langchain-core%3D%3D1.2.5"},{"url":"https://github.com/pypa/advisory-database/tree/main/vulns/langchain-core/PYSEC-2026-373.yaml"},{"url":"https://pypi.org/project/langchain-core"},{"url":"https://github.com/advisories/GHSA-c67j-w6g6-q2cm"},{"url":"https://security.access.redhat.com/data/csaf/v2/vex/2025/cve-2025-68664.json"},{"url":"https://access.redhat.com/security/cve/CVE-2025-68664"},{"url":"https://bugzilla.redhat.com/show_bug.cgi?id=2424790"},{"url":"https://www.cve.org/CVERecord?id=CVE-2025-68664"},{"url":"https://access.redhat.com/errata/RHSA-2026:0406"},{"url":"https://access.redhat.com/errata/RHSA-2026:0409"},{"url":"https://access.redhat.com/errata/RHSA-2026:0408"},{"url":"https://access.redhat.com/errata/RHSA-2026:1610"}],"tags":["osv","pip","exploit-available","ghsa","csaf","vex","red-hat"],"epss":0.4293,"epssPercentile":0.98712,"exploits":{"exploitdb":true,"github":4,"githubRepos":["https://github.com/Ak-cybe/CVE-2025-68664-LangGrinch-PoC","https://github.com/comerc/CVE-2025-68664","https://github.com/Johnnyzhou666/langgrinch-cve-2025-68664-analysis"],"checkedAt":"2026-10-27T18:16:08.387Z"},"exploitAvailable":true,"cwe":["CWE-502"],"ingestedAt":"2026-09-12T03:13:01.687Z","slug":"CVE-2025-68664","body":"## Overview\n\n## Summary\n\nA 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.\n\n### Attack surface\n\nThe core vulnerability was in `dumps()` and `dumpd()`: these functions failed to escape user-controlled dictionaries containing `'lc'` keys. When this unescaped data was later deserialized via `load()` or `loads()`, the injected structures were treated as legitimate LangChain objects rather than plain user data.\n\nThis escaping bug enabled several attack vectors:\n\n1. **Injection via user data**: Malicious LangChain object structures could be injected through user-controlled fields like `metadata`, `additional_kwargs`, or `response_metadata`\n2. **Class instantiation within trusted namespaces**: Injected manifests could instantiate any `Serializable` subclass, but only within the pre-approved trusted namespaces (`langchain_core`, `langchain`, `langchain_community`). This includes classes with side effects in `__init__` (network calls, file operations, etc.). Note that namespace validation was already enforced before this patch, so arbitrary classes outside these trusted namespaces could not be instantiated.\n\n### Security hardening\n\nThis patch fixes the escaping bug in `dumps()` and `dumpd()` and introduces new restrictive defaults in `load()` and `loads()`: allowlist enforcement via `allowed_objects=\"core\"` (restricted to [serialization mappings](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/load/mapping.py)), `secrets_from_env` changed from `True` to `False`, and default Jinja2 template blocking via `init_validator`. These are breaking changes for some use cases.\n\n## Who is affected?\n\nApplications are vulnerable if they:\n\n1. **Use `astream_events(version=\"v1\")`** — The v1 implementation internally uses vulnerable serialization. Note: `astream_events(version=\"v2\")` is not vulnerable.\n2. **Use `Runnable.astream_log()`** — This method internally uses vulnerable serialization for streaming outputs.\n3. **Call `dumps()` or `dumpd()` on untrusted data, then deserialize with `load()` or `loads()`** — Trusting your own serialization output makes you vulnerable if user-controlled data (e.g., from LLM responses, metadata fields, or user inputs) contains `'lc'` key structures.\n4. **Deserialize untrusted data with `load()` or `loads()`** — Directly deserializing untrusted data that may contain injected `'lc'` structures.\n5. **Use `RunnableWithMessageHistory`** — Internal serialization in message history handling.\n6. **Use `InMemoryVectorStore.load()`** to deserialize untrusted documents.\n7. Load untrusted generations from cache using **`langchain-community` caches**.\n8. Load untrusted manifests from the LangChain Hub via **`hub.pull`**.\n9. Use **`StringRunEvaluatorChain`** on untrusted runs.\n10. Use **`create_lc_store`** or **`create_kv_docstore`** with untrusted documents.\n11. Use **`MultiVectorRetriever`** with byte stores containing untrusted documents.\n12. Use **`LangSmithRunChatLoader`** with runs containing untrusted messages.\n\nThe most common attack vector is through **LLM response fields** like `additional_kwargs` or `response_metadata`, which can be controlled via prompt injection and then serialized/deserialized in streaming operations.\n\n## Impact\n\nAttackers who control serialized data can extract environment variable secrets by injecting `{\"lc\": 1, \"type\": \"secret\", \"id\": [\"ENV_VAR\"]}` to load environment variables during deserialization (when `secrets_from_env=True`, which was the old default). They can also instantiate classes with controlled parameters by injecting constructor structures to instantiate any class within trusted namespaces with attacker-controlled parameters, potentially triggering side effects such as network calls or file operations.\n\nKey severity factors:\n\n- Affects the serialization path - applications trusting their own serialization output are vulnerable\n- Enables secret extraction when combined with `secrets_from_env=True` (the old default)\n- LLM responses in `additional_kwargs` can be controlled via prompt injection\n\n## Exploit example\n\n```python\nfrom langchain_core.load import dumps, load\nimport os\n\n# Attacker injects secret structure into user-controlled data\nattacker_dict = {\n    \"user_data\": {\n        \"lc\": 1,\n        \"type\": \"secret\",\n        \"id\": [\"OPENAI_API_KEY\"]\n    }\n}\n\nserialized = dumps(attacker_dict)  # Bug: does NOT escape the 'lc' key\n\nos.environ[\"OPENAI_API_KEY\"] = \"sk-secret-key-12345\"\ndeserialized = load(serialized, secrets_from_env=True)\n\nprint(deserialized[\"user_data\"])  # \"sk-secret-key-12345\" - SECRET LEAKED!\n\n```\n\n## Security hardening changes (breaking changes)\n\nThis patch introduces three breaking changes to `load()` and `loads()`:\n\n1. **New `allowed_objects` parameter** (defaults to `'core'`): Enforces allowlist of classes that can be deserialized. The `'all'` option corresponds to the list of objects [specified in `mappings.py`](https://github.com/langchain-ai/langchain/blob/master/libs/core/langchain_core/load/mapping.py) while the `'core'` option limits to objects within `langchain_core`. We recommend that users explicitly specify which objects they want to allow for serialization/deserialization.\n2. **`secrets_from_env` default changed from `True` to `False`**: Disables automatic secret loading from environment\n3. **New `init_validator` parameter** (defaults to `default_init_validator`): Blocks Jinja2 templates by default\n\n## Migration guide\n\n### No changes needed for most users\n\nIf you're deserializing standard LangChain types (messages, documents, prompts, trusted partner integrations like `ChatOpenAI`, `ChatAnthropic`, etc.), your code will work without changes:\n\n```python\nfrom langchain_core.load import load\n\n# Uses default allowlist from serialization mappings\nobj = load(serialized_data)\n\n```\n\n### For custom classes\n\nIf you're deserializing custom classes not in the serialization mappings, add them to the allowlist:\n\n```python\nfrom langchain_core.load import load\nfrom my_package import MyCustomClass\n\n# Specify the classes you need\nobj = load(serialized_data, allowed_objects=[MyCustomClass])\n```\n\n### For Jinja2 templates\n\nJinja2 templates are now blocked by default because they can execute arbitrary code. If you need Jinja2 templates, pass `init_validator=None`:\n\n```python\nfrom langchain_core.load import load\nfrom langchain_core.prompts import PromptTemplate\n\nobj = load(\n    serialized_data,\n    allowed_objects=[PromptTemplate],\n    init_validator=None\n)\n\n```\n\n> [!WARNING]\n> Only disable `init_validator` if you trust the serialized data. Jinja2 templates can execute arbitrary Python code.\n\n### For secrets from environment\n\n`secrets_from_env` now defaults to `False`. If you need to load secrets from environment variables:\n\n```python\nfrom langchain_core.load import load\n\nobj = load(serialized_data, secrets_from_env=True)\n```\n\n\n## Credits\n\n* Dumps bug was reported by @yardenporat\n* Changes for security hardening due to findings from @0xn3va and @VladimirEliTokarev\n\n## Affected packages\n\n- `langchain-core >= 1.0.0, < 1.2.5`\n- `langchain-core < 0.3.81`\n\n## Remediation\n\nUpgrade to a patched release:\n\n- `langchain-core 1.2.5`\n- `langchain-core 0.3.81`\n\n## Vendor advisories\n\n- **RHSA-2026:0406** · Red Hat · fixed in: Red Hat Ansible Automation Platform 2.4 · released 2026-01-08 · [advisory](https://access.redhat.com/errata/RHSA-2026:0406)\n- **RHSA-2026:0409** · Red Hat · fixed in: Red Hat Ansible Automation Platform 2.5 · released 2026-01-08 · [advisory](https://access.redhat.com/errata/RHSA-2026:0409)\n- **RHSA-2026:0408** · Red Hat · fixed in: Red Hat Ansible Automation Platform 2.6 · released 2026-01-08 · [advisory](https://access.redhat.com/errata/RHSA-2026:0408)\n- **RHSA-2026:1610** · Red Hat · fixed in: Red Hat OpenShift Lightspeed 1.1.5 · released 2026-01-30 · [advisory](https://access.redhat.com/errata/RHSA-2026:1610)","depth":"abyssal","depthScore":72,"depthScoreParts":{"impact":51.2,"likelihood":8.6,"exploitation":12,"ransomware":0},"changes":[]}