CVE-2026-55235: langchain-ai langgraph-api, заобикаляне на вход и

Описание

Оригинално описание

langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, langgraph-api permits a run or cron to specify a relative webhook target that is delivered through an in-process loopback transport, and the authentication middleware treats that transport as internal without applying the authentication context used for external requests. In deployments that rely on per-user authorization to separate threads and runs, an authenticated user can direct a webhook to the server's own thread and run routes, allowing creation of a run on or modification of another user's thread and limited incorporation of the targeted thread's metadata into the created run record. The affected path requires webhook targets and per-user authorization boundaries; deployments that deliberately re-enable loopback delivery should restrict it to controlled same-process routes because those webhooks remain unauthenticated. This issue is fixed in version 0.10.0.

Засегнати продукти

• langchain-ai langgraph-api: < 0.10.0

Вид слабост

• CWE-287 Неправилна автентикация

История

Други уязвимости в langchain-ai langgraph-api

• 8.6CVE-2026-118668
• 5.9CVE-2026-55236

Първоизточници

• https://www.cve.org/CVERecord?id=CVE-2026-55235
• https://nvd.nist.gov/vuln/detail/CVE-2026-55235
• https://github.com/langchain-ai/helm/security/advisories/GHSA-2c9q-c2q9-qgqv
• https://github.com/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx