CVE-2026-55236

MEDIUMPre-NVD 5.95.9—
EchelonGraph scoreMEDIUM confidence

This medium-severity CVE scores 5.9 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.2%, top 94% of all CVEs by exploit prediction. GitHub Security Advisory data not yet ingested — confidence will rise once GHSA publishes (typical lag: hours to days for open-source ecosystem CVEs; never for infrastructure-only CVEs).

Triggered by: NVD CVSS baseline
Sources: epss, secondary
5.9EG
EchelonGraph verdictMonitorLow exploitation likelihood right now — keep watching.
  • Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS PROB: 0%CVSS: 5.9Exploit: None knownExposed: 0

No vendor fix yet — apply a workaround or compensating control (WAF / firewall / segmentation) and watch for a patch.

langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, the langgraph-api run-creation path authorizes the assistant attached to a run by dispatching assistants.search with an incomplete value instead of the assistants.read event used by direct reads and cron creation. In deployments with custom resource handlers that register only assistants.read, omit an assistants.search handler, and have no global fallback handler, no applicable handler supplies an owner filter, allowing a low-privileged user to reference another user's private assistant through POST /runs or POST /threads/{thread_id}/runs. The run-creation response can disclose the private assistant's metadata, config, and context, and the run can execute using that assistant's configuration. Deployments without custom authorization handlers, or with an equivalent owner filter applied through a global handler or across all assistant events, are not affected. This issue is fixed in version 0.10.0.

CVSS v3
5.9
EG Score
5.9(medium)
EG Risk
27(Track)
EG Risk 27/100SSVC: Track

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed
Severity59% × 45%
Exploitation0% × 40%
Automatability0% × 15%
Action: Routine — remediate on your standard cadence.
EPSS PROB
0%
EPSS %ILE
6%
KEV
Not listed

Published

August 19, 2026

Last Modified

September 14, 2026

Advisory Details (2)

Auto-updated Sep 14, 2026
Patch available. Sources: github.
generic

docs/src/langsmith/agent-server-changelog.mdx at 7b70fbacab21f84d9c6f9848f86cdeb471adbb50 · langchain-ai/docs · GitHub

https://github.com/langchain-ai/docs/blob/7b70fbacab21f84d9c6f9848f86cdeb471adbb50/src/langsmith/agent-server-changelog.mdx
github Patch Available

Incomplete assistant authorization in LangGraph Server run creation · Advisory · langchain-ai/helm · GitHub

https://github.com/langchain-ai/helm/security/advisories/GHSA-jfj5-wrj9-63x4

Vendor Advisories for CVE-2026-55236(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFixed inDependents
langgraph-api0.0.1 ... 0.9.1 (410 versions)0.10.0—

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 11× in last 7d / 11× in last 30d)

Each row is a source pipeline that fetched or updated this CVE on that date, with what changed. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed it from the CNA feed. Most recent first.

  1. 2026-09-20 09:07 UTCEG score recompute
  2. 2026-09-19 10:14 UTCEG score recompute
  3. 2026-09-18 19:28 UTCEPSS rescore
  4. 2026-09-18 11:02 UTCEG score recompute
  5. 2026-09-17 19:31 UTCEPSS rescore
  6. 2026-09-16 14:33 UTCEG score recompute
  7. 2026-09-16 14:08 UTCEPSS rescore
  8. 2026-09-16 05:15 UTCEPSS rescore
  9. 2026-09-14 17:55 UTCEG score recompute
  10. 2026-09-14 16:45 UTCEG score recompute
  11. 2026-09-14 16:26 UTCEG score recompute
  12. 2026-08-19 19:42 UTCEG score recompute

Related CVEs(same CWE)

Frequently asked(5)

What is CVE-2026-55236?
CVE-2026-55236 is a medium vulnerability published on August 19, 2026. langgraph-api implements the LangGraph API for rapid development and testing. Prior to 0.10.0, the langgraph-api run-creation path authorizes the assistant attached to a run by dispatching assistants.search with an incomplete value instead of the assistants.read event used by direct reads and cron…
When was CVE-2026-55236 disclosed?
CVE-2026-55236 was first published in the National Vulnerability Database on August 19, 2026, with the most recent update on September 14, 2026. EchelonGraph re-ingests CVE updates from NVD on a 2-hour cycle, so this page reflects the latest published state.
Is CVE-2026-55236 actively exploited?
CVE-2026-55236 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0% probability of exploitation in the next 30 days, which ranks it in the top 94.4% of all scored CVEs.
What is the CVSS score of CVE-2026-55236?
CVE-2026-55236 has a CVSS v3 base score of 5.9 (NVD).
How do I remediate CVE-2026-55236?
Patch to the fixed version published by the affected vendor. Where vendor advisories exist for CVE-2026-55236, EchelonGraph cross-links them in the Vendor Advisories panel below — those typically contain the canonical remediation steps, fixed version numbers, and any vendor-specific mitigations.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-55236

Explore →

Is Your Infrastructure Affected by CVE-2026-55236?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.

Start Free Scan →Browse All CVEs