CVE-2026-102697 (GCVE-0-2026-102697)
Vulnerability from cvelistv5 – Published: 2026-09-29 16:46 – Updated: 2026-09-29 17:28
VLAI
EPSS
VEX
Title
Ollama 0.14.0 before 0.31.2 Experimental Agent Bash Approval Bypass via Prefix-Based Authorization
Summary
Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode Bash tool approval mechanism that fails to properly parse shell syntax. Attackers who can influence model output through prompt injection can execute additional shell commands by appending control operators like semicolons or logical operators to approved commands, bypassing the session approval requirement.
Severity
SSVC
Exploitation: none
Automatable: no
Technical Impact: total
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-09-29 17:28 UTC
CWE
- CWE-863 - Incorrect Authorization
Assigner
References
6 references
| URL | Tags |
|---|---|
| https://github.com/ollama/ollama/commit/a2b3a5e9a… | patch |
| https://github.com/ollama/ollama/releases/tag/v0.31.2 | release-notes |
| https://github.com/ollama/ollama/blob/v0.31.1/x/a… | technical-description |
| https://github.com/ollama/ollama/blob/v0.31.1/x/a… | technical-description |
| https://github.com/ollama/ollama | product |
| https://www.vulncheck.com/advisories/ollama-0.14.… | third-party-advisory |
Impacted products
Date Public
2026-07-02 00:00
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-102697",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-29T17:28:11.306364Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-29T17:28:26.473Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"packageURL": "pkg:golang/github.com/ollama/ollama",
"product": "ollama",
"vendor": "ollama",
"versions": [
{
"lessThan": "0.31.2",
"status": "affected",
"version": "0.14.0",
"versionType": "semver"
}
]
}
],
"cpeApplicability": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:ollama:ollama:*:*:*:*:*:*:*:*",
"versionEndExcluding": "0.31.2",
"versionStartIncluding": "0.14.0",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Ak\u0131ner K\u0131sa"
}
],
"datePublic": "2026-07-02T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode Bash tool approval mechanism that fails to properly parse shell syntax. Attackers who can influence model output through prompt injection can execute additional shell commands by appending control operators like semicolons or logical operators to approved commands, bypassing the session approval requirement."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "LOCAL",
"baseScore": 8.5,
"baseSeverity": "HIGH",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "PASSIVE",
"vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH"
},
"format": "CVSS"
},
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 7.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"format": "CVSS"
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-863",
"description": "Incorrect Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-29T16:46:08.734Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "Patch Commit",
"tags": [
"patch"
],
"url": "https://github.com/ollama/ollama/commit/a2b3a5e9a3956bc0700a8505580c11faf4da09b5"
},
{
"name": "ollama v0.31.2 Release Notes",
"tags": [
"release-notes"
],
"url": "https://github.com/ollama/ollama/releases/tag/v0.31.2"
},
{
"tags": [
"technical-description"
],
"url": "https://github.com/ollama/ollama/blob/v0.31.1/x/agent/approval.go#L204-L206"
},
{
"tags": [
"technical-description"
],
"url": "https://github.com/ollama/ollama/blob/v0.31.1/x/agent/approval.go#L389"
},
{
"tags": [
"product"
],
"url": "https://github.com/ollama/ollama"
},
{
"name": "VulnCheck Advisory: Ollama 0.14.0 before 0.31.2 Experimental Agent Bash Approval Bypass via Prefix-Based Authorization",
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/ollama-0.14.0-before-0.31.2-experimental-agent-bash-approval-bypass-via-prefix-based-authorization"
}
],
"title": "Ollama 0.14.0 before 0.31.2 Experimental Agent Bash Approval Bypass via Prefix-Based Authorization",
"x_generator": {
"engine": "vulncheck-endgame"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-102697",
"datePublished": "2026-09-29T16:46:08.734Z",
"dateReserved": "2026-09-29T16:10:48.654Z",
"dateUpdated": "2026-09-29T17:28:26.473Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"defaultStatus": "unaffected",
"packageURL": "pkg:golang/github.com/ollama/ollama",
"product": "ollama",
"vendor": "ollama",
"versions": [
{
"lessThan": "0.31.2",
"status": "affected",
"version": "0.14.0",
"versionType": "semver"
}
]
}
],
"source": "disclosure@vulncheck.com"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode Bash tool approval mechanism that fails to properly parse shell syntax. Attackers who can influence model output through prompt injection can execute additional shell commands by appending control operators like semicolons or logical operators to approved commands, bypassing the session approval requirement."
}
],
"id": "CVE-2026-102697",
"lastModified": "2026-09-29T18:17:09.733",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 7.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"exploitabilityScore": 1.8,
"impactScore": 5.9,
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"cvssMetricV40": [
{
"cvssData": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "LOCAL",
"availabilityRequirement": "NOT_DEFINED",
"baseScore": 8.5,
"baseSeverity": "HIGH",
"confidentialityRequirement": "NOT_DEFINED",
"exploitMaturity": "NOT_DEFINED",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"privilegesRequired": "NONE",
"providerUrgency": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "PASSIVE",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N/E:X/CR:X/IR:X/AR:X/MAV:X/MAC:X/MAT:X/MPR:X/MUI:X/MVC:X/MVI:X/MVA:X/MSC:X/MSI:X/MSA:X/S:X/AU:X/R:X/V:X/RE:X/U:X",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-102697",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-29T17:28:11.306364Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-09-29T17:17:08.150",
"references": [
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/ollama/ollama"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/ollama/ollama/blob/v0.31.1/x/agent/approval.go#L204-L206"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/ollama/ollama/blob/v0.31.1/x/agent/approval.go#L389"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/ollama/ollama/commit/a2b3a5e9a3956bc0700a8505580c11faf4da09b5"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/ollama/ollama/releases/tag/v0.31.2"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://www.vulncheck.com/advisories/ollama-0.14.0-before-0.31.2-experimental-agent-bash-approval-bypass-via-prefix-based-authorization"
}
],
"sourceIdentifier": "disclosure@vulncheck.com",
"vulnStatus": "Received",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-863"
}
],
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
]
}
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-102697",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "no"
},
{
"Technical Impact": "total"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-09-29T17:28:11.306364Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-09-29T17:28:21.269Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"defaultStatus": "unaffected",
"packageURL": "pkg:golang/github.com/ollama/ollama",
"product": "ollama",
"vendor": "ollama",
"versions": [
{
"lessThan": "0.31.2",
"status": "affected",
"version": "0.14.0",
"versionType": "semver"
}
]
}
],
"cpeApplicability": [
{
"nodes": [
{
"cpeMatch": [
{
"criteria": "cpe:2.3:a:ollama:ollama:*:*:*:*:*:*:*:*",
"versionEndExcluding": "0.31.2",
"versionStartIncluding": "0.14.0",
"vulnerable": true
}
],
"negate": false,
"operator": "OR"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "Ak\u0131ner K\u0131sa"
}
],
"datePublic": "2026-07-02T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "Ollama versions 0.14.0 before 0.31.2 contain an incorrect authorization vulnerability in the experimental agent mode Bash tool approval mechanism that fails to properly parse shell syntax. Attackers who can influence model output through prompt injection can execute additional shell commands by appending control operators like semicolons or logical operators to approved commands, bypassing the session approval requirement."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"attackVector": "LOCAL",
"baseScore": 8.5,
"baseSeverity": "HIGH",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "PASSIVE",
"vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "HIGH",
"vulnConfidentialityImpact": "HIGH",
"vulnIntegrityImpact": "HIGH"
},
"format": "CVSS"
},
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "LOCAL",
"availabilityImpact": "HIGH",
"baseScore": 7.8,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:L/PR:N/UI:R/S:U/C:H/I:H/A:H",
"version": "3.1"
},
"format": "CVSS"
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-863",
"description": "Incorrect Authorization",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-09-29T16:46:08.734Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"name": "Patch Commit",
"tags": [
"patch"
],
"url": "https://github.com/ollama/ollama/commit/a2b3a5e9a3956bc0700a8505580c11faf4da09b5"
},
{
"name": "ollama v0.31.2 Release Notes",
"tags": [
"release-notes"
],
"url": "https://github.com/ollama/ollama/releases/tag/v0.31.2"
},
{
"tags": [
"technical-description"
],
"url": "https://github.com/ollama/ollama/blob/v0.31.1/x/agent/approval.go#L204-L206"
},
{
"tags": [
"technical-description"
],
"url": "https://github.com/ollama/ollama/blob/v0.31.1/x/agent/approval.go#L389"
},
{
"tags": [
"product"
],
"url": "https://github.com/ollama/ollama"
},
{
"name": "VulnCheck Advisory: Ollama 0.14.0 before 0.31.2 Experimental Agent Bash Approval Bypass via Prefix-Based Authorization",
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/ollama-0.14.0-before-0.31.2-experimental-agent-bash-approval-bypass-via-prefix-based-authorization"
}
],
"title": "Ollama 0.14.0 before 0.31.2 Experimental Agent Bash Approval Bypass via Prefix-Based Authorization",
"x_generator": {
"engine": "vulncheck-endgame"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-102697",
"datePublished": "2026-09-29T16:46:08.734Z",
"dateReserved": "2026-09-29T16:10:48.654Z",
"dateUpdated": "2026-09-29T17:28:26.473Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
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.
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.
Loading…