CVE-2026-55235: Medium severity pip/langgraph-api vulnerability

Published Aug 19, 2026
·
Updated

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.disableloopback 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.disableloopback: false in langgraph.json (or the equivalent LANGGRAPHWEBHOOKS 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.

Affected Software

1 affected componentFixes available
pip/langgraph-api<0.10.0
0.10.0

Remediation

Recommended actions to resolve this vulnerability, in priority order.

  1. Upgrade

    Upgrade pip/langgraph-api to a version that resolves this vulnerability.

    Fixed in 0.10.0
  2. Upgrade

    Upgrade langgraph-api to a version that resolves this vulnerability.

    Fixed in 0.10.0
  3. Configuration

    Ensure loopback webhook delivery is disabled by default. Set `webhooks.url.disable_loopback: true` in `langgraph.json` (or `LANGGRAPH_WEBHOOKS`) so relative/loopback webhook targets are denied.

    LangGraph Server runtime (langgraph-api) webhooks.url.disable_loopback = true
  4. Compensating control

    If you must enable loopback delivery for same-process webhook routes, restrict it to routes you control and apply authorization within those routes; only opt back in by setting `webhooks.url.disable_loopback: false` (in `langgraph.json` / `LANGGRAPH_WEBHOOKS`).

Event History

Aug 19, 2026
Advisory Published
via GitHub·06:55 PM
Data Sourced
via GitHub·06:55 PM
DescriptionSeverityWeaknessAffected Software

Frequently Asked Questions

1

Which deployments are meaningfully exposed?

Deployments running langgraph-api are exposed if users can create runs or crons with relative webhook targets. The cross-user impact is relevant where threads and runs are scoped by owner.

2

What does an attacker need to exploit this?

The attacker needs low-privileged access and the ability to create a run or cron using a relative webhook target. Exploitation relies on the server later delivering that webhook through its internal loopback transport.

3

What could exploitation allow?

A webhook associated with one user can reach internal thread and run routes without the authentication context applied to ordinary external requests. This may permit creating a run on, or modifying the state of, another user's thread even when direct external requests to do so are denied; limited metadata from the target thread may also be included in the created run record.

4

Has this been observed being exploited?

No evidence of this behavior occurring in the wild is reported.

Contact

SecAlerts Pty Ltd.
132 Wickham Terrace
Fortitude Valley,
QLD 4006, Australia
info@secalerts.co
By using SecAlerts services, you agree to our services end-user license agreement. This website is safeguarded by reCAPTCHA and governed by the Google Privacy Policy and Terms of Service. All names, logos, and brands of products are owned by their respective owners, and any usage of these names, logos, and brands for identification purposes only does not imply endorsement. If you possess any content that requires removal, please get in touch with us.
© 2026 SecAlerts Pty Ltd.
ABN: 70 645 966 203, ACN: 645 966 203