BREW-LANGGRAPH-CLI-CVE-2… (GHSA-3FX2-CQW9-XR3C)
Vulnerability from osv_homebrew – Published: 2026-10-29 21:38 – Updated: 2026-10-29 21:38 – Source websiteSummary
The LangGraph Python SDK v3 streaming client interpolates caller-supplied thread_id and assistant_id values into request paths without encoding them at four synchronous and asynchronous call sites. Relative path segments can therefore redirect an authenticated GET request to another path on the same configured server.
Details
The affected get_tree and _fetch_state implementations build request paths from raw identifiers rather than passing each identifier through the SDK's existing _quote_path_param helper. HTTP path normalization can collapse values containing relative segments before dispatch while retaining the client's authentication headers.
langgraph-sdk versions 0.4.0 through 0.4.5 are affected. The v3 stream module is not present in the 0.3.x release line.
RemoteGraph v3 streaming in langgraph 1.2.3 and later is also affected when used with a vulnerable langgraph-sdk version. It passes config["configurable"]["thread_id"] into threads.stream(...), and its dependency range permits affected SDK versions.
Impact
An application is affected only if it passes attacker-controlled text as a streaming thread_id or assistant_id. In that configuration, an attacker may select another readable path on the configured server and cause the SDK to return that response to the application. Through thread_id, the attacker can also control the query string, for example by targeting /store/items?namespace=...&key=...; assistant_id controls only the path. The affected requests are GET operations, so this issue does not provide a write primitive.
The LangGraph Platform is not exposed to this issue.
Remediation
Upgrade langgraph-sdk to version 0.4.6 or later. The fix encodes assistant_id in get_tree and thread_id in _fetch_state with _quote_path_param in both synchronous and asynchronous stream modules.
If you use RemoteGraph, also upgrade langgraph to version 1.2.14 or later, which requires langgraph-sdk>=0.4.6.
{
"affected": [
{
"ecosystem_specific": {
"fix": "bump",
"range_state": "fixed",
"resource": "langgraph-sdk",
"resource_purl": "pkg:pypi/langgraph-sdk@0.4.10",
"upstream_fixed_in": "0.4.6"
},
"package": {
"ecosystem": "Homebrew",
"name": "langgraph-cli",
"purl": "pkg:brew/langgraph-cli"
},
"ranges": [
{
"events": [
{
"introduced": "0.4.27"
},
{
"fixed": "0.4.33"
}
],
"type": "ECOSYSTEM"
}
]
}
],
"database_specific": {
"confidence": "high",
"source": "matched",
"strategy": "registry",
"upstream_evidence": [
{
"ecosystem": "PyPI",
"key": "pkg:pypi/langgraph-sdk@0.4.10",
"name": "langgraph-sdk",
"resource": "langgraph-sdk",
"strategy": "registry",
"subject_version": "0.4.10"
}
]
},
"details": "### Summary\n\nThe LangGraph Python SDK v3 streaming client interpolates caller-supplied `thread_id` and `assistant_id` values into request paths without encoding them at four synchronous and asynchronous call sites. Relative path segments can therefore redirect an authenticated GET request to another path on the same configured server.\n\n### Details\n\nThe affected `get_tree` and `_fetch_state` implementations build request paths from raw identifiers rather than passing each identifier through the SDK\u0027s existing `_quote_path_param` helper. HTTP path normalization can collapse values containing relative segments before dispatch while retaining the client\u0027s authentication headers.\n\n`langgraph-sdk` versions 0.4.0 through 0.4.5 are affected. The v3 stream module is not present in the 0.3.x release line.\n\n`RemoteGraph` v3 streaming in `langgraph` 1.2.3 and later is also affected when used with a vulnerable `langgraph-sdk` version. It passes `config[\"configurable\"][\"thread_id\"]` into `threads.stream(...)`, and its dependency range permits affected SDK versions.\n\n### Impact\n\nAn application is affected only if it passes attacker-controlled text as a streaming `thread_id` or `assistant_id`. In that configuration, an attacker may select another readable path on the configured server and cause the SDK to return that response to the application. Through `thread_id`, the attacker can also control the query string, for example by targeting `/store/items?namespace=...\u0026key=...`; `assistant_id` controls only the path. The affected requests are GET operations, so this issue does not provide a write primitive.\n\nThe LangGraph Platform is not exposed to this issue.\n\n### Remediation\n\nUpgrade `langgraph-sdk` to version 0.4.6 or later. The fix encodes `assistant_id` in `get_tree` and `thread_id` in `_fetch_state` with `_quote_path_param` in both synchronous and asynchronous stream modules.\n\nIf you use `RemoteGraph`, also upgrade `langgraph` to version 1.2.14 or later, which requires `langgraph-sdk\u003e=0.4.6`.",
"id": "BREW-langgraph-cli-CVE-2026-118667",
"modified": "2026-10-29T21:38:16Z",
"published": "2026-10-29T21:38:16Z",
"references": [
{
"type": "WEB",
"url": "https://github.com/langchain-ai/langgraph/security/advisories/GHSA-3fx2-cqw9-xr3c"
},
{
"type": "WEB",
"url": "https://github.com/langchain-ai/langgraph/pull/9213"
},
{
"type": "WEB",
"url": "https://github.com/langchain-ai/langgraph/commit/d89c7e100ec6fc1512544d23b0a7c5169699ef3e"
},
{
"type": "PACKAGE",
"url": "https://github.com/langchain-ai/langgraph"
},
{
"type": "WEB",
"url": "https://github.com/langchain-ai/langgraph/releases/tag/1.2.14"
},
{
"type": "WEB",
"url": "https://github.com/langchain-ai/langgraph/releases/tag/sdk%3D%3D0.4.6"
}
],
"schema_version": "1.7.3",
"severity": [
{
"score": "CVSS:3.1/AV:N/AC:L/PR:L/UI:N/S:U/C:L/I:N/A:N",
"type": "CVSS_V3"
}
],
"summary": "LangGraph: Unencoded identifiers in LangGraph SDK v3 streaming can redirect authenticated GET requests",
"upstream": [
"GHSA-3fx2-cqw9-xr3c",
"CVE-2026-118667"
]
}
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
Loading timeline…
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.