CVE-2026-15746

MEDIUMPre-NVD 6.56.5
EchelonGraph scoreMEDIUM confidence

“—” beside the score: it is equal to the CVSS score beside it.

This medium-severity CVE scores 6.5 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.4% (35th percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from a secondary CVSS source
Sources: EPSS, a secondary CVSS source
6.5EG
EchelonGraph verdictMonitorRemediate within your standard update timelines (the SSVC decision on this page).
  • Lower severity and no public exploit yet
CISA-KEV: Not listedEPSS PROB: 0.4%CVSS: 6.5Exploit: None knownExposed services: Not assessed

The CVE record names the fixed release — apply it.

Strands Agents is an open-source Python SDK for building and running AI agents. The strands-agents-tools package provides pre-built tools for use with the SDK, including the elasticsearch_memory tool for agent memory storage. We identified CVE-2026-15746, a server-side request forgery (SSRF) issue in the elasticsearch_memory tool. The tool exposed its connection parameters (es_url, cloud_id, api_key) as fields the large language model (LLM) could control through the tool schema. When a caller omitted the api_key parameter, the tool fell back to the operator's ELASTICSEARCH_API_KEY environment variable and sent it to whichever host the LLM specified. A crafted prompt could cause the tool to connect to a threat-actor-controlled server and disclose the operator's Elasticsearch API key in the Authorization header.

We recommend you upgrade to strands-agents-tools version 0.7.0 or later. As a precautionary measure, we recommend all operators rotate their ELASTICSEARCH_API_KEY, even if there is no indication the credential was exposed.

CVSS v3
6.5
EG Score
6.5MEDIUMmedium confidence
EG Risk
29
EG Risk 29/100

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)
Severity65% × 45%
The EG Score, 6.5 of 10.
Exploitation0.4% × 40%
FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.
Automatability0% × 15%
CISA's SSVC Automatable value: no (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at every mission impact level.
Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.
Action: The CVE record names the fixed release. Apply it within your standard update timelines.
EPSS PROB
0.4%
EPSS %ILE
35th
KEV
Not listed

SSVC (CISA's decision table, applied by EchelonGraph)Track at every mission impact level.

The CVE record names the fixed release. Apply it within your standard update timelines.

Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact partial (CISA Vulnrichment). All three are CISA's SSVC values (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)60 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 Vulnrichment) · Technical impact partial (CISA Vulnrichment). 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

July 15, 2026

Last Modified

July 15, 2026

Advisory Details (3)

Auto-updated Jul 15, 2026
Fix named in the CVE record. Sources: github.
Web page

strands-agents-tools · PyPI

https://pypi.org/project/strands-agents-tools/0.7.0/
GitHub advisoryMentions a patch (unverified)

Credential disclosure via LLM-controllable connection parameters in Strands Agents Tools elasticsearch_memory tool · Advisory · strands-agents/tools · GitHub

https://github.com/strands-agents/tools/security/advisories/GHSA-ppcf-fpr3-x46v
Web page

CVE-2026-15746 - Credential disclosure in Strands Agents Tools elasticsearch_memory tool

https://aws.amazon.com/security/security-bulletins/2026-056-aws/

Vendor Advisories for CVE-2026-15746(1)

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

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 12× in last 7d / 30× 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 119 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 19 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-14 16:32 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  2. 2026-10-13 16:33 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  3. 2026-10-12 16:33 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  4. 2026-10-12 16:31 UTCEG score recompute
  5. 2026-10-11 20:09 UTCEG score recompute
  6. 2026-10-11 17:22 UTCEG score recompute
  7. 2026-10-11 14:55 UTCEG score recompute
  8. 2026-10-11 13:48 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  9. 2026-10-10 19:59 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  10. 2026-10-09 20:06 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  11. 2026-10-08 17:11 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  12. 2026-10-07 23:47 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  13. 2026-10-06 15:17 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  14. 2026-10-05 17:42 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  15. 2026-10-04 23:21 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  16. 2026-10-03 14:25 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  17. 2026-10-01 19:49 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  18. 2026-10-01 12:37 UTCEG score recompute
  19. 2026-09-30 15:02 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  20. 2026-09-29 15:20 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  21. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  22. 2026-09-28 08:43 UTCEG score recompute
  23. 2026-09-27 13:47 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  24. 2026-09-26 15:58 UTCEPSS rescoreEPSS 0.4% · 34th percentile
  25. 2026-09-24 08:48 UTCEG score recompute
Show 75 more
  1. 2026-09-23 03:15 UTCEG score recompute
  2. 2026-09-18 19:27 UTCEPSS rescoreEPSS 0.4% · 36th percentile
  3. 2026-09-18 04:44 UTCEG score recompute
  4. 2026-09-16 14:07 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  5. 2026-09-16 05:14 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  6. 2026-09-14 09:26 UTCEG score recompute
  7. 2026-09-13 16:46 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  8. 2026-09-13 07:12 UTCEG score recompute
  9. 2026-09-12 15:00 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  10. 2026-09-11 21:45 UTCEG score recompute
  11. 2026-09-11 14:52 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  12. 2026-09-11 09:36 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  13. 2026-09-10 09:34 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  14. 2026-09-08 22:00 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  15. 2026-09-08 00:48 UTCEG score recompute
  16. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  17. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  18. 2026-09-05 20:49 UTCEG score recompute
  19. 2026-09-04 05:06 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  20. 2026-09-02 14:11 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  21. 2026-09-01 13:53 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  22. 2026-09-01 04:39 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  23. 2026-08-31 06:55 UTCEG score recompute
  24. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  25. 2026-08-30 03:49 UTCEG score recompute
  26. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  27. 2026-08-28 21:41 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  28. 2026-08-27 21:27 UTCEG score recompute
  29. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  30. 2026-08-26 14:46 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  31. 2026-08-26 13:47 UTCEG score recompute
  32. 2026-08-25 13:48 UTCEPSS rescoreEPSS 0.4% · 35th percentile
  33. 2026-08-25 11:32 UTCEG score recompute
  34. 2026-08-23 07:04 UTCEG score recompute
  35. 2026-08-23 00:19 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  36. 2026-08-22 04:50 UTCEG score recompute
  37. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  38. 2026-08-21 02:36 UTCEG score recompute
  39. 2026-08-20 22:55 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  40. 2026-08-20 00:15 UTCEG score recompute
  41. 2026-08-19 17:03 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  42. 2026-08-18 19:59 UTCEG score recompute
  43. 2026-08-18 13:48 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  44. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  45. 2026-08-17 11:50 UTCEG score recompute
  46. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  47. 2026-08-16 09:36 UTCEG score recompute
  48. 2026-08-16 02:14 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  49. 2026-08-15 07:23 UTCEG score recompute
  50. 2026-08-15 01:30 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  51. 2026-08-14 04:23 UTCEG score recompute
  52. 2026-08-13 22:00 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  53. 2026-08-13 02:09 UTCEG score recompute
  54. 2026-08-12 13:50 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  55. 2026-08-11 23:55 UTCEG score recompute
  56. 2026-08-11 13:42 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  57. 2026-08-11 00:00 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  58. 2026-08-09 19:27 UTCEG score recompute
  59. 2026-08-09 13:46 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  60. 2026-08-08 17:14 UTCEG score recompute
  61. 2026-08-08 16:37 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  62. 2026-08-07 15:00 UTCEG score recompute
  63. 2026-08-06 13:46 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  64. 2026-08-06 12:46 UTCEG score recompute
  65. 2026-08-05 19:17 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  66. 2026-08-05 10:32 UTCEG score recompute
  67. 2026-08-04 15:10 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  68. 2026-08-04 10:38 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  69. 2026-08-04 08:17 UTCEG score recompute
  70. 2026-08-03 10:35 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  71. 2026-08-02 03:31 UTCEG score recompute
  72. 2026-08-02 02:26 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  73. 2026-08-01 04:15 UTCEPSS rescoreEPSS 0.2% · 15th percentile
  74. 2026-07-30 23:01 UTCEG score recompute
  75. 2026-07-30 01:30 UTCEPSS rescoreEPSS 0.2% · 15th percentile

Frequently asked(5)

What is CVE-2026-15746?
CVE-2026-15746 is a medium-severity vulnerability; its CVE record was published on July 15, 2026. Strands Agents is an open-source Python SDK for building and running AI agents. The strands-agents-tools package provides pre-built tools for use with the SDK, including the elasticsearchmemory tool for agent memory storage. We identified CVE-2026-15746, a server-side request forgery (SSRF) issue…
When was the CVE record for CVE-2026-15746 published?
The CVE record for CVE-2026-15746 was published on July 15, 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 July 15, 2026; the record at its source may have been updated since.
Is CVE-2026-15746 actively exploited?
CVE-2026-15746 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.4% probability of exploitation in the next 30 days (35th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-15746?
CVE-2026-15746 has a CVSS base score of 6.5 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-15746?
The CVE record for CVE-2026-15746 names the fix: "We recommend you upgrade to strands-agents-tools version 0.7.0 or later." The vendor advisories EchelonGraph has for CVE-2026-15746 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

Explore the affected products and dependency analysis for CVE-2026-15746

Explore →

Is Your Infrastructure Affected by CVE-2026-15746?

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