Skip to main content

LangGraph Server EUVDEUVD-2026-77585

| CVE-2026-55235 MEDIUM
Improper Authentication (CWE-287)
2026-08-19 https://github.com/langchain-ai/helm GHSA-2c9q-c2q9-qgqv PYSEC-2026-3857
5.9
CVSS 3.1 · Vendor: https://github.com/langchain-ai/helm
Share

Severity by source

Vendor (https://github.com/langchain-ai/helm) PRIMARY
5.9 MEDIUM
AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L
vuln.today AI
5.9 MEDIUM

PR:L and AC:H reflect authentication and configuration prerequisites; C:L (not C:N) captures the explicit metadata leakage described; A:N because no service disruption is described.

3.1 AV:N/AC:H/PR:L/UI:N/S:U/C:L/I:H/A:N
4.0 AV:N/AC:H/AT:P/PR:L/UI:N/VC:L/VI:H/VA:N/SC:N/SI:N/SA:N

Primary rating from Vendor (https://github.com/langchain-ai/helm).

CVSS VectorVendor: https://github.com/langchain-ai/helm

Attack Vector
Network
Attack Complexity
High
Privileges Required
Low
User Interaction
None
Scope
Unchanged
Confidentiality
None
Integrity
High
Availability
Low

Lifecycle Timeline

2
Source Code Evidence Fetched
Aug 19, 2026 - 19:39 vuln.today
Analysis Generated
Aug 19, 2026 - 19:39 vuln.today

DescriptionCVE.org

Summary

In affected versions of langgraph-api (the LangGraph Server runtime), a run or cron could be created with a relative webhook target. When the server later delivers such a webhook, it routes the request back into the same application through an in-process loopback transport that the authentication middleware treats as internal and does not authenticate. As a result, a relative webhook target could reach the server's own routes that operate on threads and runs without the authentication context that applies to ordinary external requests.

In deployments that scope threads and runs by owner, this could allow a request associated with one user to reach routes operating on another user's thread, resulting in creation of a run on (or modification of the state of) a thread owned by another user, even where the corresponding direct external requests were correctly denied. Limited metadata from the targeted thread may be incorporated into the created run record.

We have no evidence of this behavior occurring in the wild.

Affected users / systems

You may be affected if you:

  • run langgraph-api (the LangGraph Server / Agent Server runtime, including via the LangGraph Platform Helm chart),
  • allow runs or crons to specify webhook targets, and
  • rely on per-user authorization to separate threads and runs between users.

Impact

  • Integrity: creation of a run on, or modification of the state of, a thread owned by another user, beyond the requesting user's authorization scope.
  • Confidentiality: limited exposure of another user's thread metadata, incorporated into the created run record.

Patches / mitigation

The webhook URL policy now denies loopback delivery by default: the webhooks.url.disable_loopback policy defaults to enabled. This covers relative webhook targets routed through the in-process transport, as well as localhost-style hostnames, loopback address ranges, and hostnames that resolve into the loopback range. Deployments that legitimately deliver webhooks to a route hosted on the same process can opt back in by setting webhooks.url.disable_loopback: false in langgraph.json (or the equivalent LANGGRAPH_WEBHOOKS configuration); do so only when you control the routes those webhooks reach, as they are delivered without authentication. Fixed in langgraph-api 0.10.0.

Operational guidance

  • Upgrade to a release containing this change and keep loopback webhook delivery disabled unless required.
  • If loopback delivery is enabled, restrict it to routes you control and apply authorization within those routes.

AnalysisAI

LangGraph Server (langgraph-api < 0.10.0) allows an authenticated user to bypass per-user authorization by specifying a relative webhook URL when creating a run or cron job, enabling cross-user thread access in multi-tenant deployments. The server's webhook delivery subsystem routes relative targets through an in-process loopback transport that the authentication middleware treats as internal and exempts from authentication, allowing the request to execute against another user's thread routes without the originating user's authorization context. …

Unlock full vulnerability intelligence

  • Risk assessment & exploitation conditions
  • Attack chain visualization
  • Remediation with exact patch versions
  • Threat intelligence from 22 sources
  • Personal watchlist & email alerts

Free forever · No credit card required

Attack ChainAIDerived

Hypothetical attack flow derived from CVE metadata

Access
technique details hidden
Delivery
technique details hidden
Exploit
technique details hidden
Execution
technique details hidden
Persist
technique details hidden
Impact
technique details hidden

Vulnerability AssessmentAI

Exploitation Exploitation requires three concurrent conditions to be satisfied: (1) the attacker holds a valid authenticated account with permission to create runs or cron jobs on the langgraph-api server (CVSS PR:L confirms unauthenticated exploitation is not possible); (2) the server is configured to accept webhook targets in run or cron creation requests (this feature must be enabled and user-accessible); and (3) the deployment uses per-user authorization to scope threads and runs by owner. … Additional conditions and limiting factors are described in the full assessment.
Risk Assessment The provided CVSS 3.1 score of 5.9 Medium reflects two materially risk-reducing factors: AC:H (high complexity due to specific configuration prerequisites) and PR:L (authentication required - this is not an unauthenticated attack surface). … Full risk analysis with EPSS, KEV, and SSVC signal comparison available after sign-in.
Exploit Scenario Full exploit scenario with step-by-step reproduction available after sign-in.
Remediation Upgrade langgraph-api to version 0.10.0 or later, which introduces the webhooks.url.disable_loopback policy that defaults to enabled. … Detailed patch versions, workarounds, and compensating controls in full report.

Threat intelligence, references, and detailed analysis are available after sign-in.

Share

EUVD-2026-77585 vulnerability details – vuln.today

This site uses cookies essential for authentication and security. No tracking or analytics cookies are used. Privacy Policy