{"id":"CVE-2026-12570","aliases":["CLSA-2026-1794219735","DEBIAN-CVE-2026-12570","EUVD-2026-55002","GHSA-74m6-m3xx-3vmj","OESA-2026-3952","OESA-2026-3953","OESA-2026-4052","PYSEC-2026-3856","UBUNTU-CVE-2026-12570"],"status":"published","title":"Denial of Service via HDF5 Shape Bomb in keras.models.load_model() in keras-team/keras","description":"A vulnerability in keras-team/keras versions \u003c= 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.","severity":{"version":"3.0","score":5.5,"vector":"CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium","assessor":"cna","from":"cve"},"epss":{"day":"2026-11-11","score":0.0019,"percentile":0.08789,"model":"v2026.06.15"},"facts":{"in_kev":false,"known_exploited":false,"public_exploit":false,"fix_available":true},"cwes":["CWE-770"],"published":"2026-08-10T06:29:56Z","modified":"2026-11-09T19:15:11Z","fixes":[{"ecosystem":"PyPI","package":"keras","fixed_in":["3.15.0"],"sources":["ghsa","osv"]},{"ecosystem":"TuxCare:PyPI","package":"keras","fixed_in":["2.15.0.post4+tuxcare"],"sources":["osv"]},{"ecosystem":"openEuler:24.03-LTS-SP1","package":"python-Keras","fixed_in":["2.12.0-5.oe2403sp1"],"sources":["osv"]},{"ecosystem":"openEuler:24.03-LTS-SP3","package":"python-Keras","fixed_in":["2.12.0-5.oe2403sp3"],"sources":["osv"]},{"ecosystem":"openEuler:24.03-LTS-SP4","package":"python-Keras","fixed_in":["2.12.0-5.oe2403sp4"],"sources":["osv"]}],"affected":[{"source":"ghsa","ecosystem":"PyPI","package":"keras","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.15.0"}]}]},{"source":"osv","ecosystem":"TuxCare:PyPI","package":"keras","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"2.15.0"},{"fixed":"2.15.0.post4+tuxcare"}]}],"versions":["2.15.0","2.15.0.post1+tuxcare","2.15.0.post2+tuxcare","2.15.0.post3+tuxcare"]},{"source":"osv","ecosystem":"Debian:11","package":"keras","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["2.3.1+dfsg-3","2.3.1+dfsg2-1"]},{"source":"osv","ecosystem":"PyPI","package":"keras","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.15.0"}]}],"versions":["0.2.0","0.3.0","0.3.1","0.3.2","0.3.3","1.0.0","1.0.1","1.0.2","1.0.3","1.0.4","1.0.5","1.0.6","1.0.7","1.0.8","1.1.0","1.1.1","1.1.2","1.2.0","1.2.1","1.2.2","2.0.0","2.0.1","2.0.2","2.0.3","2.0.4","2.0.5","2.0.6","2.0.7","2.0.8","2.0.9","2.1.0","2.1.1","2.1.2","2.1.3","2.1.4","2.1.5","2.1.6","2.10.0","2.10.0rc0","2.10.0rc1","2.11.0","2.11.0rc0","2.11.0rc1","2.11.0rc2","2.11.0rc3","2.12.0","2.12.0rc0","2.12.0rc1","2.13.1","2.13.1rc0","2.13.1rc1","2.14.0","2.14.0rc0","2.15.0","2.15.0rc0","2.15.0rc1","2.2.0","2.2.1","2.2.2","2.2.3","2.2.4","2.2.5","2.3.0","2.3.1","2.4.0","2.4.1","2.4.2","2.4.3","2.5.0rc0","2.6.0","2.6.0rc0","2.6.0rc1","2.6.0rc2","2.6.0rc3","2.7.0","2.7.0rc0","2.7.0rc2","2.8.0","2.8.0rc0","2.8.0rc1","2.9.0","2.9.0rc0","2.9.0rc1","2.9.0rc2","3.0.0","3.0.1","3.0.2","3.0.3","3.0.4","3.0.5","3.1.0","3.1.1","3.10.0","3.11.0","3.11.1","3.11.2","3.11.3","3.12.0","3.12.1","3.12.2","3.12.3","3.12.4","3.13.0","3.13.1","3.13.2","3.14.0","3.14.1","3.2.0","3.2.1","3.3.0","3.3.1","3.3.2","3.3.3","3.4.0","3.4.1","3.5.0","3.6.0","3.7.0","3.8.0","3.9.0","3.9.1","3.9.2"]},{"source":"osv","ecosystem":"openEuler:24.03-LTS-SP1","package":"python-Keras","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"2.12.0-5.oe2403sp1"}]}]},{"source":"osv","ecosystem":"openEuler:24.03-LTS-SP3","package":"python-Keras","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"2.12.0-5.oe2403sp3"}]}]},{"source":"osv","ecosystem":"openEuler:24.03-LTS-SP4","package":"python-Keras","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"2.12.0-5.oe2403sp4"}]}]},{"source":"osv","ecosystem":"PyPI","package":"keras","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"},{"fixed":"3.15.0"}]}],"versions":["0.2.0","0.3.0","0.3.1","0.3.2","0.3.3","1.0.0","1.0.1","1.0.2","1.0.3","1.0.4","1.0.5","1.0.6","1.0.7","1.0.8","1.1.0","1.1.1","1.1.2","1.2.0","1.2.1","1.2.2","2.0.0","2.0.1","2.0.2","2.0.3","2.0.4","2.0.5","2.0.6","2.0.7","2.0.8","2.0.9","2.1.0","2.1.1","2.1.2","2.1.3","2.1.4","2.1.5","2.1.6","2.10.0","2.10.0rc0","2.10.0rc1","2.11.0","2.11.0rc0","2.11.0rc1","2.11.0rc2","2.11.0rc3","2.12.0","2.12.0rc0","2.12.0rc1","2.13.1","2.13.1rc0","2.13.1rc1","2.14.0","2.14.0rc0","2.15.0","2.15.0rc0","2.15.0rc1","2.2.0","2.2.1","2.2.2","2.2.3","2.2.4","2.2.5","2.3.0","2.3.1","2.4.0","2.4.1","2.4.2","2.4.3","2.5.0rc0","2.6.0","2.6.0rc0","2.6.0rc1","2.6.0rc2","2.6.0rc3","2.7.0","2.7.0rc0","2.7.0rc2","2.8.0","2.8.0rc0","2.8.0rc1","2.9.0","2.9.0rc0","2.9.0rc1","2.9.0rc2","3.0.0","3.0.1","3.0.2","3.0.3","3.0.4","3.0.5","3.1.0","3.1.1","3.10.0","3.11.0","3.11.1","3.11.2","3.11.3","3.12.0","3.12.1","3.12.2","3.12.3","3.12.4","3.13.0","3.13.1","3.13.2","3.14.0","3.14.1","3.2.0","3.2.1","3.3.0","3.3.1","3.3.2","3.3.3","3.4.0","3.4.1","3.5.0","3.6.0","3.7.0","3.8.0","3.9.0","3.9.1","3.9.2"]},{"source":"osv","ecosystem":"Ubuntu:18.04:LTS","package":"keras","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["1.0.7-2","2.1.1-1"]},{"source":"osv","ecosystem":"Ubuntu:20.04:LTS","package":"keras","ranges":[{"type":"ECOSYSTEM","events":[{"introduced":"0"}]}],"versions":["2.2.4-1"]}],"products":[{"vendor":"keras-team","product":"keras-team/keras"}],"references":[{"url":"https://huntr.com/bounties/a064f475-780a-409a-82f7-678512f27ad8","tags":["exploit","web","report"]},{"url":"https://github.com/keras-team/keras/commit/4933ea4a5b3fcc24ceacdc276f5bb5dfbd06756c","tags":["fix","web","report"]},{"url":"https://nvd.nist.gov/vuln/detail/CVE-2026-12570","tags":["advisory"]},{"url":"https://github.com/keras-team/keras/pull/22975","tags":["web"]},{"url":"https://github.com/keras-team/keras/releases/tag/v3.15.0","tags":["web"]},{"url":"https://github.com/advisories/GHSA-74m6-m3xx-3vmj","tags":["advisory"]},{"url":"https://github.com/CVEProject/cvelistV5/tree/main/cves/2026/12xxx/CVE-2026-12570.json","tags":["advisory"]},{"url":"https://security-tracker.debian.org/tracker/CVE-2026-12570","tags":["advisory"]},{"url":"https://github.com/keras-team/keras","tags":["package"]},{"url":"https://www.openeuler.org/zh/security/security-bulletins/detail/?id=openEuler-SA-2026-3952","tags":["advisory"]},{"url":"https://www.openeuler.org/zh/security/security-bulletins/detail/?id=openEuler-SA-2026-3953","tags":["advisory"]},{"url":"https://www.openeuler.org/zh/security/security-bulletins/detail/?id=openEuler-SA-2026-4052","tags":["advisory"]},{"url":"https://pypi.org/project/keras","tags":["package"]},{"url":"https://ubuntu.com/security/CVE-2026-12570","tags":["report"]},{"url":"https://www.cve.org/CVERecord?id=CVE-2026-12570","tags":["report"]}],"sources":{"cve":[{"id":"CVE-2026-12570","title":"Denial of Service via HDF5 Shape Bomb in keras.models.load_model() in keras-team/keras","description":"A vulnerability in keras-team/keras versions \u003c= 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.","status":"published","published":"2026-08-10T06:29:56.111Z","modified":"2026-08-10T17:37:39.037Z","cvss":[{"version":"3.0","score":5.5,"vector":"CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium","assessor":"cna"}],"cwes":["CWE-770"],"updated_at":"2026-11-02T14:19:47.998488Z"}],"euvd":[{"id":"EUVD-2026-55002","description":"A vulnerability in keras-team/keras versions \u003c= 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.","status":"published","published":"2026-08-10T06:29:56Z","modified":"2026-08-10T17:37:39Z","cvss":[{"version":"3.0","score":5.5,"vector":"CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T18:02:01.58399Z"}],"ghsa":[{"id":"GHSA-74m6-m3xx-3vmj","title":"Keras model loading is vulnerable to denial of service through HDF5 shape bombs","description":"A vulnerability in keras-team/keras versions \u003c 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.","status":"published","published":"2026-08-10T09:31:20Z","modified":"2026-09-01T20:22:07Z","cvss":[{"version":"3.0","score":5.5,"vector":"CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-770"],"updated_at":"2026-11-02T14:41:08.980668Z"}],"nvd":[{"id":"CVE-2026-12570","description":"A vulnerability in keras-team/keras versions \u003c= 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.","status":"published","published":"2026-08-10T07:16:44.37Z","modified":"2026-10-23T20:10:00.16Z","cvss":[{"version":"3.0","score":5.5,"vector":"CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium","assessor":"secondary"}],"cwes":["CWE-770"],"updated_at":"2026-11-02T14:12:35.743275Z"}],"osv":[{"id":"CVE-2026-12570","title":"Denial of Service via HDF5 Shape Bomb in keras.models.load_model() in keras-team/keras","description":"A vulnerability in keras-team/keras versions \u003c= 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.","status":"published","published":"2026-08-10T06:29:56.111Z","modified":"2026-10-28T02:30:34.437908232Z","cvss":[{"version":"3.0","score":5.5,"vector":"CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-770"],"updated_at":"2026-11-02T15:44:57.354194Z"},{"id":"DEBIAN-CVE-2026-12570","description":"A vulnerability in keras-team/keras versions \u003c= 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.","status":"published","published":"2026-08-10T07:16:44.37Z","modified":"2026-08-27T23:05:49.844172892Z","cvss":[{"version":"3.0","score":5.5,"vector":"CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T15:45:51.374409Z"},{"id":"GHSA-74m6-m3xx-3vmj","title":"Keras model loading is vulnerable to denial of service through HDF5 shape bombs","description":"A vulnerability in keras-team/keras versions \u003c 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.","status":"published","published":"2026-08-10T09:31:20Z","modified":"2026-09-10T12:25:26.313959426Z","cvss":[{"version":"3.0","score":5.5,"vector":"CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium"}],"cwes":["CWE-770"],"updated_at":"2026-11-02T15:46:40.657155Z"},{"id":"OESA-2026-3952","title":"python-Keras security update","description":"Keras is a high-level neural networks API for Python.\r\n\r\nSecurity Fix(es):\n\nA vulnerability in keras-team/keras versions \u0026lt;= 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.(CVE-2026-12570)","status":"published","published":"2026-09-20T13:23:32Z","modified":"2026-09-20T13:30:27.385245154Z","cvss":[{"version":"3.1","score":5.5,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T15:52:47.643553Z"},{"id":"OESA-2026-3953","title":"python-Keras security update","description":"Keras is a high-level neural networks API for Python.\r\n\r\nSecurity Fix(es):\n\nA vulnerability in keras-team/keras versions \u0026lt;= 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.(CVE-2026-12570)","status":"published","published":"2026-09-20T13:23:32Z","modified":"2026-09-20T13:30:30.09881561Z","cvss":[{"version":"3.1","score":5.5,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T15:52:47.643553Z"},{"id":"OESA-2026-4052","title":"python-Keras security update","description":"Keras is a high-level neural networks API for Python.\r\n\r\nSecurity Fix(es):\n\nA vulnerability in keras-team/keras versions \u0026lt;= 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.(CVE-2026-12570)","status":"published","published":"2026-09-25T01:27:41Z","modified":"2026-09-25T01:45:07.404489084Z","cvss":[{"version":"3.1","score":5.5,"vector":"CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T15:52:47.643553Z"},{"id":"PYSEC-2026-3856","title":"Keras model loading is vulnerable to denial of service through HDF5 shape bombs","description":"A vulnerability in keras-team/keras versions \u003c 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.","status":"published","published":"2026-09-10T09:44:51.470942Z","modified":"2026-09-10T12:15:06.946960903Z","cvss":[{"version":"3.0","score":5.5,"vector":"CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T15:52:57.255153Z"},{"id":"UBUNTU-CVE-2026-12570","description":"A vulnerability in keras-team/keras versions \u003c= 3.15.0 allows for a denial of service (DoS) attack when loading malicious .keras model files via the keras.models.load_model() function. The H5IOStore.__getitem__ method in keras/src/saving/saving_lib.py does not validate the shape or size of datasets, leading to unbounded memory allocation. A specially crafted .keras file can exploit this flaw to trigger an out-of-memory (OOM) condition, causing the process to be terminated (exit code 137). This issue bypasses the fix for CVE-2026-0897, which only addressed a similar vulnerability in KerasFileEditor. The attack vector includes poisoned models from public repositories or malicious model registries, posing a risk to machine learning pipelines that process untrusted models.","status":"published","published":"2026-08-10T07:16:00Z","modified":"2026-08-13T03:00:46.349514839Z","cvss":[{"version":"3.0","score":5.5,"vector":"CVSS:3.0/AV:L/AC:L/PR:N/UI:R/S:U/C:N/I:N/A:H","level":"medium"}],"updated_at":"2026-11-02T16:56:00.592716Z"},{"id":"CLSA-2026-1794219735","title":"TuxCare security update for keras (1 CVE)","description":"TuxCare rebuilt keras to address 1 CVE. Fixed in 2.15.0.post4+tuxcare.","status":"published","published":"2026-11-09T11:22:16Z","modified":"2026-11-09T19:15:11.133651415Z","updated_at":"2026-11-09T19:38:09.278998Z"}]}}