CVE-2026-48776

CRITICALNVD 9.19.1—
EchelonGraph scoreMEDIUM confidence

This critical-severity CVE scores 9.1 under NVD CVSS v3. EPSS exploit probability: 0.3% (20th percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from NVD CVSS v3
Sources: EPSS, NVD CVSS v3
9.1EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines (the SSVC decision on this page).
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 0.3%CVSS: 9.1Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. Versions 0.3.14 and prior have unsafe URL path construction through unsanitized caller-supplied identifier values used in HTTP request paths for resource operations. Without sanitization of those values, identifiers that contain characters with special meaning in URL paths could cause the resulting request to address a different resource (and potentially a different resource type) than the SDK method's call site indicates. In deployments where the SDK receives identifier values that originate from untrusted sources, this could result in unintended access, modification, or deletion of resources beyond the calling user's authorization scope. This issue is most consequential in deployments that forward end-user-supplied values directly into SDK identifier parameters without first validating them against an expected format (such as a UUID), and rely on URL-prefix-based authorization at an upstream layer (reverse proxy, edge gateway, WAF), where the authorization decision is made on the SDK call's intended path rather than on the final delivered request path. The issue has been fixed in version 0.3.15.

CVSS v3
9.1
EG Score
9.1CRITICALmedium confidence
EG Risk
41
EG Risk 41/100

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 (value × EchelonGraph’s weight)
Severity91% × 45%
The EG Score, 9.1 of 10.
Exploitation0.3% × 40%
FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.
Automatability0% × 15%
CISA's BOD 26-04 default: no one has published Automatable for this CVE, and CISA treats it as “no” for a CVE not in KEV.
SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Track* at high (mission-essential systems).
Exploitation none (no CISA value, KEV listing or exploit code on record) · Automatable no (CISA's BOD 26-04 default) · Technical impact total (CISA's BOD 26-04 default). EchelonGraph holds no SSVC assessment of this CVE from CISA: none of these inputs is from Vulnrichment. EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.
Action: A fix is available. Apply it within your standard update timelines.
EPSS PROB
0.3%
EPSS %ILE
20th
KEV
Not listed

SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Track* at high (mission-essential systems).

A fix is available. Apply it within your standard update timelines.

Exploitation none (no CISA value, KEV listing or exploit code on record) · Automatable no (CISA's BOD 26-04 default) · Technical impact total (CISA's BOD 26-04 default). EchelonGraph holds no SSVC assessment of this CVE from CISA: none of these inputs is from Vulnrichment. EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table

BOD 26-04 (CISA's remediation timeline, Table 1)14 days if the affected system is publicly exposed; Fix on system upgrade if it is not.

In CISA KEV no (CISA's KEV catalog) · Automatable no (CISA's BOD 26-04 default) · Technical impact total (CISA's BOD 26-04 default). Where an input reads “CISA's BOD 26-04 default”, no one has published it for this CVE, and CISA's implementation guidance says: “If “Automatable” and “Technical Impact” information items about a CVE ID are not available and the CVE ID is not in the KEV Catalog, CISA will treat its values as “no” and “total,” respectively, until CISA or a third party provides metadata about the CVE ID. CISA will always provide the Vulnrichment data for a CVE ID listed in the KEV Catalog.” Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it

Published

June 17, 2026

Last Modified

June 26, 2026

Advisory Details (2)

Auto-updated Sep 16, 2026
Patch available. Sources: github_release, github.
GitHub advisoryMentions a patch (unverified)

Unsafe URL path construction in LangGraph SDK · Advisory · langchain-ai/langgraph · GitHub

https://github.com/langchain-ai/langgraph/security/advisories/GHSA-w39p-vh2g-g8g5
GitHub release Patch Available

langgraph-sdk==0.3.15

Patch available: langchain-ai/langgraph sdk==0.3.15

https://github.com/langchain-ai/langgraph/releases/tag/sdk%3D%3D0.3.15

Vendor Advisories for CVE-2026-48776(1)

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

Affected Packages

(2 across 1 ecosystem)
PyPI(2)
PackageVulnerable rangeFix by version rangeDependents
langgraph0.0.10 ... 0.3.9 (175 versions)
  • every version up to 0.3.15: fixed in 0.3.15
—
langgraph-sdk0.1.0 ... 0.3.9 (96 versions)
  • every version up to 0.3.15: fixed in 0.3.15
—

Weakness Classification(2)

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

Data Freshness Timeline

(refreshed 11× in last 7d / 26× in last 30d)

Each row is a time one of our pipelines fetched, updated or re-scored this CVE. 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. An arrow marks a change the record states ("CVSS v3 → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). Most recent first.

Showing the most recent 100 of 145 refreshes on record for this CVE.

A repeat, a row identical to one the same pipeline wrote less than 10 seconds earlier, is not a separate refresh and is not counted. None are among the latest 100 rows. The 45 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-11 19:43 UTCEG score recompute
  2. 2026-10-11 16:58 UTCEG score recompute
  3. 2026-10-11 14:22 UTCEG score recompute
  4. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  5. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  6. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  7. 2026-10-08 17:12 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  8. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.3% · 20th percentile
  9. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  10. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  11. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  12. 2026-10-03 17:18 UTCOSV refresh
  13. 2026-10-03 14:25 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  14. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  15. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  16. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  17. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  18. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  19. 2026-09-26 00:27 UTCEPSS rescoreEPSS 0.3% · 19th percentile
  20. 2026-09-23 17:53 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  21. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  22. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  23. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  24. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  25. 2026-09-14 03:21 UTCEG score recompute
Show 75 more
  1. 2026-09-13 16:47 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  2. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  3. 2026-09-10 09:35 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  4. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  5. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  6. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  7. 2026-09-04 05:06 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  8. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  9. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  10. 2026-09-01 04:40 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  11. 2026-08-30 22:33 UTCEG score recompute
  12. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  13. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  14. 2026-08-28 21:41 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  15. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  16. 2026-08-26 14:46 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  17. 2026-08-25 13:49 UTCEPSS rescoreEPSS 0.2% · 11th percentile
  18. 2026-08-24 23:17 UTCEG score recompute
  19. 2026-08-23 09:01 UTCEG score recompute
  20. 2026-08-23 00:19 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  21. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  22. 2026-08-21 01:07 UTCEG score recompute
  23. 2026-08-20 22:55 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  24. 2026-08-20 08:27 UTCEG score recompute
  25. 2026-08-19 17:04 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  26. 2026-08-19 08:25 UTCEG score recompute
  27. 2026-08-18 13:48 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  28. 2026-08-17 14:57 UTCEG score recompute
  29. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  30. 2026-08-16 16:18 UTCEG score recompute
  31. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  32. 2026-08-16 03:14 UTCEG score recompute
  33. 2026-08-16 02:14 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  34. 2026-08-15 02:11 UTCEG score recompute
  35. 2026-08-15 01:30 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  36. 2026-08-13 23:54 UTCEG score recompute
  37. 2026-08-13 22:00 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  38. 2026-08-12 15:12 UTCEG score recompute
  39. 2026-08-12 13:51 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  40. 2026-08-11 16:52 UTCEG score recompute
  41. 2026-08-11 03:46 UTCEG score recompute
  42. 2026-08-11 00:00 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  43. 2026-08-09 14:09 UTCEG score recompute
  44. 2026-08-09 13:46 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  45. 2026-08-08 20:46 UTCEG score recompute
  46. 2026-08-08 16:37 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  47. 2026-08-07 18:41 UTCEG score recompute
  48. 2026-08-06 16:30 UTCEG score recompute
  49. 2026-08-06 13:47 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  50. 2026-08-05 23:08 UTCEG score recompute
  51. 2026-08-05 19:17 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  52. 2026-08-04 15:31 UTCEG score recompute
  53. 2026-08-04 15:10 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  54. 2026-08-04 10:39 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  55. 2026-08-03 14:31 UTCEG score recompute
  56. 2026-08-03 10:36 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  57. 2026-08-02 05:51 UTCEG score recompute
  58. 2026-08-02 02:27 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  59. 2026-08-01 08:06 UTCEG score recompute
  60. 2026-08-01 04:16 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  61. 2026-07-30 22:54 UTCEG score recompute
  62. 2026-07-30 16:28 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  63. 2026-07-30 03:59 UTCEG score recompute
  64. 2026-07-30 01:30 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  65. 2026-07-29 02:39 UTCEG score recompute
  66. 2026-07-28 15:37 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  67. 2026-07-27 18:12 UTCEG score recompute
  68. 2026-07-26 19:31 UTCEG score recompute
  69. 2026-07-26 14:54 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  70. 2026-07-25 14:18 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  71. 2026-07-24 14:18 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  72. 2026-07-23 14:18 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  73. 2026-07-23 03:18 UTCEG score recompute
  74. 2026-07-22 14:08 UTCEPSS rescoreEPSS 0.2% · 12th percentile
  75. 2026-07-21 15:25 UTCEPSS rescoreEPSS 0.2% · 12th percentile

Frequently asked(5)

What is CVE-2026-48776?
CVE-2026-48776 is a critical-severity vulnerability; its CVE record was published on June 17, 2026. LangGraph Python SDK is used to connect to running LangGraph API servers, manage assistants, threads and stream runs from Python applications. Versions 0.3.14 and prior have unsafe URL path construction through unsanitized caller-supplied identifier values used in HTTP request paths for resource…
When was the CVE record for CVE-2026-48776 published?
The CVE record for CVE-2026-48776 was published on June 17, 2026. That is the record's publication date; the vulnerability itself may have been made public earlier. EchelonGraph's copy of the record carries a last-modified date of June 26, 2026; the record at its source may have been updated since.
Is CVE-2026-48776 actively exploited?
CVE-2026-48776 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.3% probability of exploitation in the next 30 days (20th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-48776?
CVE-2026-48776 has a CVSS v3 base score of 9.1 (NVD).
How do I remediate CVE-2026-48776?
A fix for CVE-2026-48776 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-48776 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2026-48776

Explore →

Is Your Infrastructure Affected by CVE-2026-48776?

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