CVE-2026-59318 (GCVE-0-2026-59318)
Vulnerability from cvelistv5 – Published: 2026-08-21 12:07 – Updated: 2026-08-22 03:55
VLAI
EPSS
VEX
Title
DefaultToolCallingManager Global Resolver Fallback Allows Unadvertised Tool Dispatch via Prompt Injection
Summary
In Spring AI's tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege escalation.
Affected versions:
Spring AI: 2.0.0
Spring AI: 1.1.0 through 1.1.8
Spring AI: 1.0.0 through 1.0.9
Severity
6.5 (Medium)
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-08-21 00:00 UTC
CWE
- CWE-863 - Incorrect Authorization
Assigner
References
1 reference
Impacted products
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-59318",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-21T00:00:00+00:00",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-22T03:55:38.874Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "Spring AI",
"vendor": "Spring",
"versions": [
{
"status": "affected",
"version": "2.0.0",
"versionType": "custom"
},
{
"lessThanOrEqual": "1.1.8",
"status": "affected",
"version": "1.1.0",
"versionType": "custom"
},
{
"lessThanOrEqual": "1.0.9",
"status": "affected",
"version": "1.0.0",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cp\u003eIn Spring AI\u0027s tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege escalation.\u003c/p\u003e\u003cp\u003eAffected versions:\u003c/p\u003e\u003cul\u003e\u003cli\u003eSpring AI: 2.0.0\u003c/li\u003e\u003cli\u003eSpring AI: 1.1.0 through 1.1.8\u003c/li\u003e\u003cli\u003eSpring AI: 1.0.0 through 1.0.9\u003c/li\u003e\u003c/ul\u003e"
}
],
"value": "In Spring AI\u0027s tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege escalation.\nAffected versions:\nSpring AI: 2.0.0\nSpring AI: 1.1.0 through 1.1.8\nSpring AI: 1.0.0 through 1.0.9"
}
],
"impacts": [
{
"descriptions": [
{
"lang": "en",
"value": "In Spring AI\u0027s tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege escalation."
}
]
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:L/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-863",
"description": "Incorrect Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-21T12:07:10.349Z",
"orgId": "dcf2e128-44bd-42ed-91e8-88f912c1401d",
"shortName": "vmware"
},
"references": [
{
"url": "https://spring.io/security/cve-2026-59318"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "DefaultToolCallingManager Global Resolver Fallback Allows Unadvertised Tool Dispatch via Prompt Injection"
}
},
"cveMetadata": {
"assignerOrgId": "dcf2e128-44bd-42ed-91e8-88f912c1401d",
"assignerShortName": "vmware",
"cveId": "CVE-2026-59318",
"datePublished": "2026-08-21T12:07:10.349Z",
"dateReserved": "2026-07-04T18:13:57.026Z",
"dateUpdated": "2026-08-22T03:55:38.874Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-59318",
"date": "2026-10-24",
"epss": "0.00254",
"percentile": "0.1606"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"defaultStatus": "unaffected",
"product": "Spring AI",
"vendor": "Spring",
"versions": [
{
"status": "affected",
"version": "2.0.0",
"versionType": "custom"
},
{
"lessThanOrEqual": "1.1.8",
"status": "affected",
"version": "1.1.0",
"versionType": "custom"
},
{
"lessThanOrEqual": "1.0.9",
"status": "affected",
"version": "1.0.0",
"versionType": "custom"
}
]
}
],
"source": "security@vmware.com"
}
],
"configurations": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:vmware:spring_ai:*:-:*:*:*:*:*:*",
"matchCriteriaId": "62A8F36A-EB49-43FF-8E20-123B4556C78E",
"versionEndExcluding": "1.0.10",
"versionStartIncluding": "1.0.0",
"vulnerable": true
},
{
"criteria": "cpe:2.3:a:vmware:spring_ai:*:-:*:*:*:*:*:*",
"matchCriteriaId": "ACE55DA1-63B6-4607-9AF7-82593833BC9E",
"versionEndExcluding": "1.1.9",
"versionStartIncluding": "1.1.0",
"vulnerable": true
},
{
"criteria": "cpe:2.3:a:vmware:spring_ai:*:-:*:*:*:*:*:*",
"matchCriteriaId": "982C3A10-D1CC-47BA-89FC-E6687E8ADBE5",
"versionEndExcluding": "2.0.1",
"versionStartIncluding": "2.0.0",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "In Spring AI\u0027s tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege escalation.\nAffected versions:\nSpring AI: 2.0.0\nSpring AI: 1.1.0 through 1.1.8\nSpring AI: 1.0.0 through 1.0.9"
},
{
"lang": "es",
"value": "En el soporte de llamada a herramientas de Spring AI, la lista de herramientas por solicitud se anuncia al modelo como un l\u00edmite, pero no se aplica completamente cuando se despacha una llamada a herramienta. Bajo ciertas condiciones, una herramienta que no se puso a disposici\u00f3n de la solicitud actual podr\u00eda ser invocada, lo que podr\u00eda llevar a una escalada de privilegios.\nVersiones afectadas:\nSpring AI: 2.0.0\nSpring AI: 1.1.0 a 1.1.8\nSpring AI: 1.0.0 a 1.0.9"
}
],
"id": "CVE-2026-59318",
"lastModified": "2026-10-15T19:10:00.173",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:L/A:N",
"version": "3.1"
},
"exploitabilityScore": 1.3,
"impactScore": 4.7,
"source": "security@vmware.com",
"type": "Secondary"
},
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "HIGH",
"baseScore": 9.8,
"baseSeverity": "CRITICAL",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"exploitabilityScore": 3.9,
"impactScore": 5.9,
"source": "nvd@nist.gov",
"type": "Primary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-59318",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-21T00:00:00+00:00",
"version": "2.0.3"
}
}
]
},
"published": "2026-08-21T12:16:30.390",
"references": [
{
"source": "security@vmware.com",
"tags": [
"Vendor Advisory"
],
"url": "https://spring.io/security/cve-2026-59318"
}
],
"sourceIdentifier": "security@vmware.com",
"vulnStatus": "Analyzed",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-863"
}
],
"source": "security@vmware.com",
"type": "Secondary"
}
]
}
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-59318",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-08-21T14:31:31.704007Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-08-21T14:31:41.944Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"product": "Spring AI",
"vendor": "Spring",
"versions": [
{
"status": "affected",
"version": "2.0.0",
"versionType": "custom"
},
{
"lessThanOrEqual": "1.1.8",
"status": "affected",
"version": "1.1.0",
"versionType": "custom"
},
{
"lessThanOrEqual": "1.0.9",
"status": "affected",
"version": "1.0.0",
"versionType": "custom"
}
]
}
],
"descriptions": [
{
"lang": "en",
"supportingMedia": [
{
"base64": false,
"type": "text/html",
"value": "\u003cp\u003eIn Spring AI\u0027s tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege escalation.\u003c/p\u003e\u003cp\u003eAffected versions:\u003c/p\u003e\u003cul\u003e\u003cli\u003eSpring AI: 2.0.0\u003c/li\u003e\u003cli\u003eSpring AI: 1.1.0 through 1.1.8\u003c/li\u003e\u003cli\u003eSpring AI: 1.0.0 through 1.0.9\u003c/li\u003e\u003c/ul\u003e"
}
],
"value": "In Spring AI\u0027s tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege escalation.\nAffected versions:\nSpring AI: 2.0.0\nSpring AI: 1.1.0 through 1.1.8\nSpring AI: 1.0.0 through 1.0.9"
}
],
"impacts": [
{
"descriptions": [
{
"lang": "en",
"value": "In Spring AI\u0027s tool calling support, the per-request tool list is advertised to the model as a boundary but is not fully enforced when a tool call is dispatched. Under certain conditions, a tool that was not made available to the current request could be invoked, potentially leading to privilege escalation."
}
]
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 6.5,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "HIGH",
"integrityImpact": "LOW",
"privilegesRequired": "LOW",
"scope": "CHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:R/S:C/C:H/I:L/A:N",
"version": "3.1"
},
"format": "CVSS",
"scenarios": [
{
"lang": "en",
"value": "GENERAL"
}
]
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-863",
"description": "Incorrect Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-08-21T12:07:10.349Z",
"orgId": "dcf2e128-44bd-42ed-91e8-88f912c1401d",
"shortName": "vmware"
},
"references": [
{
"url": "https://spring.io/security/cve-2026-59318"
}
],
"source": {
"discovery": "UNKNOWN"
},
"title": "DefaultToolCallingManager Global Resolver Fallback Allows Unadvertised Tool Dispatch via Prompt Injection"
}
},
"cveMetadata": {
"assignerOrgId": "dcf2e128-44bd-42ed-91e8-88f912c1401d",
"assignerShortName": "vmware",
"cveId": "CVE-2026-59318",
"datePublished": "2026-08-21T12:07:10.349Z",
"dateReserved": "2026-07-04T18:13:57.026Z",
"dateUpdated": "2026-08-21T14:31:46.967Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Drag nodes to arrange them. Double-click a related vulnerability to open it, or a source to visit its link. The Physics button on the left tunes the layout and the simulation; the legend at the bottom left hides or shows nodes by kind and by sighting type.
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Vulnerability timeline
Sightings and recorded dates, grouped by day · UTC
Loading timeline…
Loading…
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Loading…
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.