{"id":"CVE-2025-67644","aliases":["EUVD-2025-202333","GHSA-9rwj-6rc7-p77c","PYSEC-2026-1530"],"status":"published","title":"LangGraph SQLite Checkpoint is vulnerable to SQL Injection via metadata filter key in checkpointer list method","description":"LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Versions 3.0.0 and below are vulnerable to SQL injection through the checkpoint implementation. Checkpoint allows attackers to manipulate SQL queries through metadata filter keys, affecting applications that accept untrusted metadata filter keys (not just filter values) in checkpoint search operations. The _metadata_predicate() function constructs SQL queries by interpolating filter keys directly into f-strings without validation. This issue is fixed in version 3.0.1.","severity":{"version":"3.1","score":7.3,"vector":"CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N","level":"high","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-09","score":0.02306,"percentile":0.8347,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":true,"fix_available":true},"cwes":["CWE-89"],"published":"2025-12-10T00:02:21Z","modified":"2026-10-28T02:31:13Z","exploits":[{"source":"pocgithub","id":"mbanyamer/CVE-2025-67644-LangGraph-3.0.1-SQLite-Checkpoint-SQL-Injection","title":"mbanyamer/CVE-2025-67644-LangGraph-3.0.1-SQLite-Checkpoint-SQL-Injection","date":"2026-02-22","url":"https://github.com/mbanyamer/CVE-2025-67644-LangGraph-3.0.1-SQLite-Checkpoint-SQL-Injection"}],"fixes":[{"ecosystem":"PyPI","package":"langgraph-checkpoint-sqlite","fixed_in":["3.0.1"],"sources":["ghsa","osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"langgraph-checkpoint-sqlite","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.0.1"}]}]},{"source":"osv","ecosystem":"PyPI","package":"langgraph-checkpoint-sqlite","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.0.1"}]}],"versions":["1.0.0","1.0.1","1.0.2","1.0.3","1.0.4","2.0.0","2.0.1","2.0.10","2.0.11","2.0.2","2.0.3","2.0.4","2.0.5","2.0.6","2.0.7","2.0.8","2.0.9","3.0.0"]},{"source":"osv","ecosystem":"PyPI","package":"langgraph-checkpoint-sqlite","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.0.1"}]}],"versions":["1.0.0","1.0.1","1.0.2","1.0.3","1.0.4","2.0.0","2.0.1","2.0.10","2.0.11","2.0.2","2.0.3","2.0.4","2.0.5","2.0.6","2.0.7","2.0.8","2.0.9","3.0.0"]}],"products":[{"vendor":"langchain","product":"langgraph-checkpoint-sqlite"},{"vendor":"langchain-ai","product":"langgraph"}],"references":[{"url":"https://github.com/langchain-ai/langgraph/security/advisories/GHSA-9rwj-6rc7-p77c","tags":["x_refsource_CONFIRM","Exploit","Vendor Advisory","advisory","web"]},{"url":"https://github.com/langchain-ai/langgraph/commit/297242913f8ad2143ee3e2f72e67db0911d48e2a","tags":["x_refsource_MISC","Patch","fix","web"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2025-67644","tags":["advisory"]},{"url":"https://github.com/advisories/GHSA-9rwj-6rc7-p77c","tags":["advisory"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2025/67xxx/CVE-2025-67644.json","tags":["advisory"]},{"url":"https://github.com/langchain-ai/langgraph","tags":["package"]},{"url":"https://pypi.org/project/langgraph-checkpoint-sqlite","tags":["package"]}],"sources":{"cve":[{"id":"CVE-2025-67644","title":"LangGraph SQLite Checkpoint is vulnerable to SQL Injection via metadata filter key in checkpointer list method","description":"LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Versions 3.0.0 and below are vulnerable to SQL injection through the checkpoint implementation. Checkpoint allows attackers to manipulate SQL queries through metadata filter keys, affecting applications that accept untrusted metadata filter keys (not just filter values) in checkpoint search operations. The _metadata_predicate() function constructs SQL queries by interpolating filter keys directly into f-strings without validation. This issue is fixed in version 3.0.1.","status":"published","published":"2025-12-10T23:37:36.182Z","modified":"2025-12-11T15:35:59.816Z","cvss":[{"version":"3.1","score":7.3,"vector":"CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N","level":"high","assessor":"cna"}],"cwes":["CWE-89"],"updated_at":"2026-11-02T14:32:51.880027Z"}],"euvd":[{"id":"EUVD-2025-202333","description":"LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Versions 3.0.0 and below are vulnerable to SQL injection through the checkpoint implementation. Checkpoint allows attackers to manipulate SQL queries through metadata filter keys, affecting applications that accept untrusted metadata filter keys (not just filter values) in checkpoint search operations. The _metadata_predicate() function constructs SQL queries by interpolating filter keys directly into f-strings without validation. This issue is fixed in version 3.0.1.","status":"published","published":"2025-12-10T23:37:36Z","modified":"2025-12-11T15:35:59Z","cvss":[{"version":"3.1","score":7.3,"vector":"CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N","level":"high"}],"updated_at":"2026-11-02T19:49:06.661228Z"}],"ghsa":[{"id":"GHSA-9rwj-6rc7-p77c","title":"LangGraph's SQLite is vulnerable to SQL injection via metadata filter key in SQLite checkpointer list method","description":"# Context\n\nA SQL injection vulnerability exists in LangGraph's SQLite checkpoint implementation that allows attackers to manipulate SQL queries through metadata filter keys. This affects applications that accept **untrusted metadata filter keys** (not just filter values) in checkpoint search operations.\n\n# Impact\n\nAttackers who control metadata filter keys can execute arbitrary sql queries against the database.\n\n# Root Cause\n\nThe `_metadata_predicate()` function constructs SQL queries by interpolating filter keys directly into f-strings without validation:\n\n```python\n# VULNERABLE CODE (before fix)\nfor query_key, query_value in metadata_filter.items():\n    operator, param_value = _where_value(query_value)\n    predicates.append(\n        f\"json_extract(CAST(metadata AS TEXT), '$.{query_key}') {operator}\"\n    )\n    param_values.append(param_value)\n```\n\nWhile filter **values** are parameterized, filter **keys** are not validated, allowing SQL injection.\n\n# Attack Example\n\n**Before Fix:**\n```python\nfrom langgraph.checkpoint.sqlite import SqliteSaver\n\nsaver = SqliteSaver.from_conn_string(\"checkpoints.db\")\n\n# Attacker controls the filter keys\nmalicious_filter = {\"x') OR '1'='1\": \"dummy\"}\n\n# Returns ALL checkpoints, bypassing filtering\nresults = list(saver.list(None, filter=malicious_filter))\n```\n\n**Resulting SQL:**\n```sql\nWHERE json_extract(CAST(metadata AS TEXT), '$.x') OR '1'='1') = ?\n-- Injected condition makes WHERE clause always true\n```\n\n## Who Is Affected?\n\n### LangSmith Deployment Customers: NOT Impacted\n\n**LangSmith deployment customers are NOT affected by this vulnerability.** LangSmith deployments do not allow configuring custom checkpointers, so the vulnerable code path cannot be reached.\n\n### High Risk: Custom Server Deployments\n\nYou are affected if your application:\n- Runs a custom server with SqliteSaver checkpointer\n- Exposes an endpoint for fetching checkpoint history (e.g., via `get_state_history()`)\n- Accepts metadata filter keys from untrusted sources\n\n**Example vulnerable code:**\n```python\n# Custom server endpoint - User controls filter key names - DANGEROUS\n@app.post(\"/api/history\")\ndef get_history(request):\n    filter_field = request.json.get(\"filter_field\")  # Untrusted input\n    filter_value = request.json.get(\"filter_value\")\n\n    # VULNERABLE: Attacker can bypass access controls\n    history = list(graph.get_state_history(\n        config,\n        filter={filter_field: filter_value}\n    ))\n    return history\n```\n\n**Note on privilege escalation:** If an endpoint allows end users to specify arbitrary filter keys, those users likely already have legitimate access to query the checkpoint database. In such cases, this vulnerability may not constitute a privilege escalation, as users who can control filter keys would typically already be expected to have database access. However, the SQL injection still allows bypassing intended filtering logic and metadata-based access controls that the application may rely on for data isolation.\n\n### Additional Security Hardening (Defense in Depth)\n\nThis release also includes hardening improvements:\n\n**1. Checkpoint Limit Parameter**: used f-string interpolation into parameterized query.  Not considered a vulnerability as it requires users to accept untrusted input and not validate it against the actual API signature. \n\n**2. Store Filter Value Parameterization**: Refactored all filter value handling from manual quote escaping to parameterized queries\n\n## Remediation\n\n### Immediate Actions\n\n1. **Update to the patched version** of `langgraph-checkpoint-sqlite`\n2. **Audit your code** for locations where filter keys come from untrusted sources","status":"published","published":"2025-12-10T00:02:21Z","modified":"2025-12-24T06:22:16Z","cvss":[{"version":"3.1","score":7.3,"vector":"CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N","level":"high"}],"cwes":["CWE-89"],"updated_at":"2026-11-02T14:39:14.093341Z"}],"nvd":[{"id":"CVE-2025-67644","description":"LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Versions 3.0.0 and below are vulnerable to SQL injection through the checkpoint implementation. Checkpoint allows attackers to manipulate SQL queries through metadata filter keys, affecting applications that accept untrusted metadata filter keys (not just filter values) in checkpoint search operations. The _metadata_predicate() function constructs SQL queries by interpolating filter keys directly into f-strings without validation. This issue is fixed in version 3.0.1.","status":"published","published":"2025-12-11T00:16:23.23Z","modified":"2026-10-08T10:10:00.227Z","cvss":[{"version":"3.1","score":7.3,"vector":"CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N","level":"high","assessor":"secondary"},{"version":"3.1","score":7.8,"vector":"CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:U/C:H/I:H/A:H","level":"high","assessor":"primary"}],"cwes":["CWE-89"],"updated_at":"2026-11-02T14:11:49.861863Z"}],"osv":[{"id":"CVE-2025-67644","title":"LangGraph SQLite Checkpoint is vulnerable to SQL Injection via metadata filter key in checkpointer list method","description":"LangGraph SQLite Checkpoint is an implementation of LangGraph CheckpointSaver that uses SQLite DB (both sync and async, via aiosqlite). Versions 3.0.0 and below are vulnerable to SQL injection through the checkpoint implementation. Checkpoint allows attackers to manipulate SQL queries through metadata filter keys, affecting applications that accept untrusted metadata filter keys (not just filter values) in checkpoint search operations. The _metadata_predicate() function constructs SQL queries by interpolating filter keys directly into f-strings without validation. This issue is fixed in version 3.0.1.","status":"published","published":"2025-12-10T23:37:36.182Z","modified":"2026-10-28T02:31:13.726900703Z","cvss":[{"version":"3.1","score":7.3,"vector":"CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N","level":"high"}],"cwes":["CWE-89"],"updated_at":"2026-11-02T15:44:52.53036Z"},{"id":"GHSA-9rwj-6rc7-p77c","title":"LangGraph's SQLite is vulnerable to SQL injection via metadata filter key in SQLite checkpointer list method","description":"# Context\n\nA SQL injection vulnerability exists in LangGraph's SQLite checkpoint implementation that allows attackers to manipulate SQL queries through metadata filter keys. This affects applications that accept **untrusted metadata filter keys** (not just filter values) in checkpoint search operations.\n\n# Impact\n\nAttackers who control metadata filter keys can execute arbitrary sql queries against the database.\n\n# Root Cause\n\nThe `_metadata_predicate()` function constructs SQL queries by interpolating filter keys directly into f-strings without validation:\n\n```python\n# VULNERABLE CODE (before fix)\nfor query_key, query_value in metadata_filter.items():\n    operator, param_value = _where_value(query_value)\n    predicates.append(\n        f\"json_extract(CAST(metadata AS TEXT), '$.{query_key}') {operator}\"\n    )\n    param_values.append(param_value)\n```\n\nWhile filter **values** are parameterized, filter **keys** are not validated, allowing SQL injection.\n\n# Attack Example\n\n**Before Fix:**\n```python\nfrom langgraph.checkpoint.sqlite import SqliteSaver\n\nsaver = SqliteSaver.from_conn_string(\"checkpoints.db\")\n\n# Attacker controls the filter keys\nmalicious_filter = {\"x') OR '1'='1\": \"dummy\"}\n\n# Returns ALL checkpoints, bypassing filtering\nresults = list(saver.list(None, filter=malicious_filter))\n```\n\n**Resulting SQL:**\n```sql\nWHERE json_extract(CAST(metadata AS TEXT), '$.x') OR '1'='1') = ?\n-- Injected condition makes WHERE clause always true\n```\n\n## Who Is Affected?\n\n### LangSmith Deployment Customers: NOT Impacted\n\n**LangSmith deployment customers are NOT affected by this vulnerability.** LangSmith deployments do not allow configuring custom checkpointers, so the vulnerable code path cannot be reached.\n\n### High Risk: Custom Server Deployments\n\nYou are affected if your application:\n- Runs a custom server with SqliteSaver checkpointer\n- Exposes an endpoint for fetching checkpoint history (e.g., via `get_state_history()`)\n- Accepts metadata filter keys from untrusted sources\n\n**Example vulnerable code:**\n```python\n# Custom server endpoint - User controls filter key names - DANGEROUS\n@app.post(\"/api/history\")\ndef get_history(request):\n    filter_field = request.json.get(\"filter_field\")  # Untrusted input\n    filter_value = request.json.get(\"filter_value\")\n\n    # VULNERABLE: Attacker can bypass access controls\n    history = list(graph.get_state_history(\n        config,\n        filter={filter_field: filter_value}\n    ))\n    return history\n```\n\n**Note on privilege escalation:** If an endpoint allows end users to specify arbitrary filter keys, those users likely already have legitimate access to query the checkpoint database. In such cases, this vulnerability may not constitute a privilege escalation, as users who can control filter keys would typically already be expected to have database access. However, the SQL injection still allows bypassing intended filtering logic and metadata-based access controls that the application may rely on for data isolation.\n\n### Additional Security Hardening (Defense in Depth)\n\nThis release also includes hardening improvements:\n\n**1. Checkpoint Limit Parameter**: used f-string interpolation into parameterized query.  Not considered a vulnerability as it requires users to accept untrusted input and not validate it against the actual API signature. \n\n**2. Store Filter Value Parameterization**: Refactored all filter value handling from manual quote escaping to parameterized queries\n\n## Remediation\n\n### Immediate Actions\n\n1. **Update to the patched version** of `langgraph-checkpoint-sqlite`\n2. **Audit your code** for locations where filter keys come from untrusted sources","status":"published","published":"2025-12-10T00:02:21Z","modified":"2026-07-07T17:56:34.997556097Z","cvss":[{"version":"3.1","score":7.3,"vector":"CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N","level":"high"}],"cwes":["CWE-89"],"updated_at":"2026-11-02T15:46:44.225359Z"},{"id":"PYSEC-2026-1530","title":"LangGraph's SQLite is vulnerable to SQL injection via metadata filter key in SQLite checkpointer list method","description":"# Context\n\nA SQL injection vulnerability exists in LangGraph's SQLite checkpoint implementation that allows attackers to manipulate SQL queries through metadata filter keys. This affects applications that accept **untrusted metadata filter keys** (not just filter values) in checkpoint search operations.\n\n# Impact\n\nAttackers who control metadata filter keys can execute arbitrary sql queries against the database.\n\n# Root Cause\n\nThe `_metadata_predicate()` function constructs SQL queries by interpolating filter keys directly into f-strings without validation:\n\n```python\n# VULNERABLE CODE (before fix)\nfor query_key, query_value in metadata_filter.items():\n    operator, param_value = _where_value(query_value)\n    predicates.append(\n        f\"json_extract(CAST(metadata AS TEXT), '$.{query_key}') {operator}\"\n    )\n    param_values.append(param_value)\n```\n\nWhile filter **values** are parameterized, filter **keys** are not validated, allowing SQL injection.\n\n# Attack Example\n\n**Before Fix:**\n```python\nfrom langgraph.checkpoint.sqlite import SqliteSaver\n\nsaver = SqliteSaver.from_conn_string(\"checkpoints.db\")\n\n# Attacker controls the filter keys\nmalicious_filter = {\"x') OR '1'='1\": \"dummy\"}\n\n# Returns ALL checkpoints, bypassing filtering\nresults = list(saver.list(None, filter=malicious_filter))\n```\n\n**Resulting SQL:**\n```sql\nWHERE json_extract(CAST(metadata AS TEXT), '$.x') OR '1'='1') = ?\n-- Injected condition makes WHERE clause always true\n```\n\n## Who Is Affected?\n\n### LangSmith Deployment Customers: NOT Impacted\n\n**LangSmith deployment customers are NOT affected by this vulnerability.** LangSmith deployments do not allow configuring custom checkpointers, so the vulnerable code path cannot be reached.\n\n### High Risk: Custom Server Deployments\n\nYou are affected if your application:\n- Runs a custom server with SqliteSaver checkpointer\n- Exposes an endpoint for fetching checkpoint history (e.g., via `get_state_history()`)\n- Accepts metadata filter keys from untrusted sources\n\n**Example vulnerable code:**\n```python\n# Custom server endpoint - User controls filter key names - DANGEROUS\n@app.post(\"/api/history\")\ndef get_history(request):\n    filter_field = request.json.get(\"filter_field\")  # Untrusted input\n    filter_value = request.json.get(\"filter_value\")\n\n    # VULNERABLE: Attacker can bypass access controls\n    history = list(graph.get_state_history(\n        config,\n        filter={filter_field: filter_value}\n    ))\n    return history\n```\n\n**Note on privilege escalation:** If an endpoint allows end users to specify arbitrary filter keys, those users likely already have legitimate access to query the checkpoint database. In such cases, this vulnerability may not constitute a privilege escalation, as users who can control filter keys would typically already be expected to have database access. However, the SQL injection still allows bypassing intended filtering logic and metadata-based access controls that the application may rely on for data isolation.\n\n### Additional Security Hardening (Defense in Depth)\n\nThis release also includes hardening improvements:\n\n**1. Checkpoint Limit Parameter**: used f-string interpolation into parameterized query.  Not considered a vulnerability as it requires users to accept untrusted input and not validate it against the actual API signature. \n\n**2. Store Filter Value Parameterization**: Refactored all filter value handling from manual quote escaping to parameterized queries\n\n## Remediation\n\n### Immediate Actions\n\n1. **Update to the patched version** of `langgraph-checkpoint-sqlite`\n2. **Audit your code** for locations where filter keys come from untrusted sources","status":"published","published":"2026-07-07T16:03:12.694748Z","modified":"2026-07-07T17:46:36.795807386Z","cvss":[{"version":"3.1","score":7.3,"vector":"CVSS:3.1/AV:L/AC:L/PR:L/UI:N/S:C/C:H/I:L/A:N","level":"high"}],"updated_at":"2026-11-02T15:52:55.06457Z"}]}}