{"answers":{"affected":"3 open source packages ship an affected version, including langgraph-api.","exploited":"There is no known exploitation of CVE-2026-55235 in the wild and no public exploit code.","fix":"Upgrade langgraph-api to 0.10.0 or later.","what":"CVE-2026-55235 is a medium-severity missing authorization vulnerability in langchain-ai langgraph-api, published on 14 Sep 2026. Any signed-in user can exploit it over the network, with no action from the victim."},"fix_prompt":"Check this codebase for CVE-2026-55235 and fix it if it is affected.\n\nWhat it is: CVE-2026-55235 is a medium-severity missing authorization vulnerability in langchain-ai langgraph-api, published on 14 Sep 2026. Any signed-in user can exploit it over the network, with no action from the victim.\nExploitation: There is no known exploitation of CVE-2026-55235 in the wild and no public exploit code.\n\nAffected packages and fixed versions:\n- langgraph-api (PyPI): affected all versions; fixed in 0.10.0\n- langgraph-api (PyPI): affected all versions; fixed in 0.10.0\n- langgraph-api (PyPI): affected all versions; fixed in 0.10.0\n\nTask:\n1. Search the dependency manifests and lockfiles (for example package.json, package-lock.json, requirements.txt, poetry.lock, uv.lock, pom.xml, build.gradle, go.mod, Cargo.lock, Gemfile.lock) and any Dockerfiles for the affected packages, including transitive dependencies.\n2. If an affected version is in use, upgrade it to the fixed version for its release line with the project's package manager, so the lockfile is regenerated. Prefer the smallest upgrade that fixes it.\n3. If there is no fix, or the upgrade would break the build, do not guess: explain the risk and the safest workaround instead.\n4. Run the tests and summarise what changed and why.\n5. If nothing in the project is affected, say so and change nothing.\n\nReference: https://insights.sbomify.com/CVE-2026-55235/ (Markdown: https://insights.sbomify.com/CVE-2026-55235/index.md)","id":"CVE-2026-55235","markdown":"https://insights.sbomify.com/CVE-2026-55235/index.md","name":"CVE-2026-55235","record":{"aliases":["GHSA-2c9q-c2q9-qgqv","PYSEC-2026-3857"],"analysis":{"component_type":"library","fix_type":"upgrade","impacts":["data_modify","security_bypass"],"network_reachable":"yes","non_default_config":true,"product_category":"LangGraph API library","requires_auth":"low_privilege","summary":"Authenticated users can bypass authorization checks to modify other users' threads via relative webhook targets in LangGraph Server.","user_interaction":"not_required","vuln_class":"missing_authorization"},"analysis_generated_by":"qwen3.8-flash-next","assigner":"GitHub_M","cpe":[],"cvss":{"score":5.9,"severity":"medium","source":"cna","vector":"CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:U/C:N/I:H/A:L","version":"3.1"},"cwes":[{"id":"CWE-287","name":"Improper Authentication"}],"description":"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.","ecosystems":["PyPI"],"exploits":{"exploitdb":0,"first_seen":null,"github_poc":0,"max_poc_stars":null,"metasploit":0,"nuclei":0,"refs":[],"tier":"none_known"},"has_fix":true,"headline":"langgraph-api: Relative webhook targets in LangGraph Server can reach in-process routes without authentication","id":"CVE-2026-55235","indexable":true,"kev":null,"kind":"cve","links":{"ecosystem":"PyPI","product":null,"products":[],"type":"missing_authorization","year":"2026"},"n_packages":3,"n_references":2,"next":{"headline":"langgraph-api: Incomplete assistant authorization in LangGraph Server run creation","id":"CVE-2026-55236"},"packages":[{"ecosystem":"PyPI","fixed":["0.10.0"],"introduced":["0"],"last_affected":[],"package":"langgraph-api","purl":null,"source":"GHSA-2c9q-c2q9-qgqv"},{"ecosystem":"PyPI","fixed":["0.10.0"],"introduced":["0"],"last_affected":[],"package":"langgraph-api","purl":"pkg:pypi/langgraph-api","source":"GHSA-2c9q-c2q9-qgqv"},{"ecosystem":"PyPI","fixed":["0.10.0"],"introduced":["0"],"last_affected":[],"package":"langgraph-api","purl":"pkg:pypi/langgraph-api","source":"PYSEC-2026-3857"}],"prev":{"headline":"Missing authorization in wekan","id":"CVE-2026-55234"},"products":["langgraph-api"],"published":"2026-09-14","related":[],"sources":[{"class":"attribution","licence":"CVE Terms of Use (MITRE)","name":"CVE List","prefix":"CVE"},{"class":"attribution","licence":"CC BY 4.0","name":"GitHub Advisory Database","prefix":"GHSA"},{"class":"attribution","licence":"CC BY 4.0","name":"PyPA Advisory Database","prefix":"PYSEC"},{"class":"attribution","licence":"CWE Terms of Use","name":"CWE (MITRE)"},{"class":"attribution","licence":"FIRST CVSS licence","name":"CVSS (FIRST)"}],"ssvc":{"automatable":"no","exploitation":"none","technical_impact":"partial"},"state":"PUBLISHED","updated":"2026-09-16","vendors":["langchain-ai"]},"summary":"Authenticated users can bypass authorization checks to modify other users' threads via relative webhook targets in LangGraph Server.","url":"https://insights.sbomify.com/CVE-2026-55235/"}