CVE-2026-108600 (GCVE-0-2026-108600)
Vulnerability from cvelistv5 – Published: 2026-10-10 18:58 – Updated: 2026-10-10 18:58
VLAI
EPSS
VEX
Title
open-multi-agent 1.5.0 through 1.21.2 Sandbox Escape via file_write Dangling Symlink
Summary
open-multi-agent (@open-multi-agent/core) 1.5.0 through 1.21.2 contains a link following vulnerability in the file_write tool sandbox that allows attackers to create files outside the workspace root by using dangling symlinks. Attackers can plant a dangling symlink in the workspace and steer the agent via prompt injection to write attacker-influenced content anywhere the agent process can write.
Severity
4.7 (Medium)
CWE
- CWE-59 - Improper Link Resolution Before File Access ('Link Following')
Assigner
References
5 references
| URL | Tags |
|---|---|
| https://hackmd.io/@haind/open-multi-agent-file-wr… | third-party-advisory |
| https://github.com/open-multi-agent/open-multi-ag… | technical-description |
| https://github.com/open-multi-agent/open-multi-ag… | technical-description |
| https://github.com/open-multi-agent/open-multi-agent | product |
| https://www.vulncheck.com/advisories/open-multi-a… | third-party-advisory |
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| open-multi-agent | open-multi-agent |
Affected:
1.5.0 , ≤ 1.21.2
(semver)
|
guessed |
Date Public
2026-10-09 00:00
{
"containers": {
"cna": {
"affected": [
{
"collectionURL": "https://www.npmjs.com",
"defaultStatus": "unaffected",
"packageURL": "pkg:npm/%40open-multi-agent/core",
"product": "open-multi-agent",
"repo": "https://github.com/open-multi-agent/open-multi-agent",
"vendor": "open-multi-agent",
"versions": [
{
"lessThanOrEqual": "1.21.2",
"status": "affected",
"version": "1.5.0",
"versionType": "semver"
}
]
}
],
"credits": [
{
"lang": "en",
"type": "finder",
"value": "HaiND from the Post and Telecommunication Institute of Technology"
}
],
"datePublic": "2026-10-09T00:00:00.000Z",
"descriptions": [
{
"lang": "en",
"value": "open-multi-agent (@open-multi-agent/core) 1.5.0 through 1.21.2 contains a link following vulnerability in the file_write tool sandbox that allows attackers to create files outside the workspace root by using dangling symlinks. Attackers can plant a dangling symlink in the workspace and steer the agent via prompt injection to write attacker-influenced content anywhere the agent process can write."
}
],
"metrics": [
{
"cvssV4_0": {
"attackComplexity": "LOW",
"attackRequirements": "PRESENT",
"attackVector": "LOCAL",
"baseScore": 5.7,
"baseSeverity": "MEDIUM",
"privilegesRequired": "NONE",
"subAvailabilityImpact": "NONE",
"subConfidentialityImpact": "NONE",
"subIntegrityImpact": "NONE",
"userInteraction": "PASSIVE",
"vectorString": "CVSS:4.0/AV:L/AC:L/AT:P/PR:N/UI:P/VC:N/VI:H/VA:N/SC:N/SI:N/SA:N",
"version": "4.0",
"vulnAvailabilityImpact": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "HIGH"
},
"format": "CVSS"
},
{
"cvssV3_1": {
"attackComplexity": "HIGH",
"attackVector": "LOCAL",
"availabilityImpact": "NONE",
"baseScore": 4.7,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N",
"version": "3.1"
},
"format": "CVSS"
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-59",
"description": "Improper Link Resolution Before File Access (\u0027Link Following\u0027)",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-10-10T18:58:16.432Z",
"orgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"shortName": "VulnCheck"
},
"references": [
{
"tags": [
"third-party-advisory"
],
"url": "https://hackmd.io/@haind/open-multi-agent-file-write-dangling-symlink-escape"
},
{
"tags": [
"technical-description"
],
"url": "https://github.com/open-multi-agent/open-multi-agent/blob/6ec5498643c7e431aa66751f17f47a529e7f927c/packages/core/src/tool/built-in/path-safety.ts#L104-L113"
},
{
"tags": [
"technical-description"
],
"url": "https://github.com/open-multi-agent/open-multi-agent/blob/6ec5498643c7e431aa66751f17f47a529e7f927c/packages/core/src/tool/built-in/file-write.ts#L67"
},
{
"tags": [
"product"
],
"url": "https://github.com/open-multi-agent/open-multi-agent"
},
{
"name": "VulnCheck Advisory: open-multi-agent 1.5.0 through 1.21.2 Sandbox Escape via file_write Dangling Symlink",
"tags": [
"third-party-advisory"
],
"url": "https://www.vulncheck.com/advisories/open-multi-agent-1.5.0-through-1.21.2-sandbox-escape-via-file-write-dangling-symlink"
}
],
"title": "open-multi-agent 1.5.0 through 1.21.2 Sandbox Escape via file_write Dangling Symlink",
"x_generator": {
"engine": "vulncheck-endgame"
}
}
},
"cveMetadata": {
"assignerOrgId": "83251b91-4cc7-4094-a5c7-464a1b83ea10",
"assignerShortName": "VulnCheck",
"cveId": "CVE-2026-108600",
"datePublished": "2026-10-10T18:58:16.432Z",
"dateReserved": "2026-10-10T18:25:15.230Z",
"dateUpdated": "2026-10-10T18:58:16.432Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"epss": {
"cve": "CVE-2026-108600",
"date": "2026-10-11",
"epss": "0.00148",
"percentile": "0.03518"
},
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"collectionURL": "https://www.npmjs.com",
"defaultStatus": "unaffected",
"packageURL": "pkg:npm/%40open-multi-agent/core",
"product": "open-multi-agent",
"repo": "https://github.com/open-multi-agent/open-multi-agent",
"vendor": "open-multi-agent",
"versions": [
{
"lessThanOrEqual": "1.21.2",
"status": "affected",
"version": "1.5.0",
"versionType": "semver"
}
]
}
],
"source": "disclosure@vulncheck.com"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "open-multi-agent (@open-multi-agent/core) 1.5.0 through 1.21.2 contains a link following vulnerability in the file_write tool sandbox that allows attackers to create files outside the workspace root by using dangling symlinks. Attackers can plant a dangling symlink in the workspace and steer the agent via prompt injection to write attacker-influenced content anywhere the agent process can write."
}
],
"id": "CVE-2026-108600",
"lastModified": "2026-10-10T19:16:58.640",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "HIGH",
"attackVector": "LOCAL",
"availabilityImpact": "NONE",
"baseScore": 4.7,
"baseSeverity": "MEDIUM",
"confidentialityImpact": "NONE",
"integrityImpact": "HIGH",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "REQUIRED",
"vectorString": "CVSS:3.1/AV:L/AC:H/PR:N/UI:R/S:U/C:N/I:H/A:N",
"version": "3.1"
},
"exploitabilityScore": 1.0,
"impactScore": 3.6,
"source": "disclosure@vulncheck.com",
"type": "Primary"
}
],
"cvssMetricV40": [
{
"cvssData": {
"Automatable": "NOT_DEFINED",
"Recovery": "NOT_DEFINED",
"Safety": "NOT_DEFINED",
"attackComplexity": "LOW",
"attackRequirements": "PRESENT",
"attackVector": "LOCAL",
"availabilityRequirement": "NOT_DEFINED",
"baseScore": 5.7,
"baseSeverity": "MEDIUM",
"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:P/PR:N/UI:P/VC:N/VI:H/VA:N/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": "NONE",
"vulnConfidentialityImpact": "NONE",
"vulnIntegrityImpact": "HIGH",
"vulnerabilityResponseEffort": "NOT_DEFINED"
},
"source": "disclosure@vulncheck.com",
"type": "Secondary"
}
]
},
"published": "2026-10-10T19:16:58.640",
"references": [
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/open-multi-agent/open-multi-agent"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/open-multi-agent/open-multi-agent/blob/6ec5498643c7e431aa66751f17f47a529e7f927c/packages/core/src/tool/built-in/file-write.ts#L67"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://github.com/open-multi-agent/open-multi-agent/blob/6ec5498643c7e431aa66751f17f47a529e7f927c/packages/core/src/tool/built-in/path-safety.ts#L104-L113"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://hackmd.io/@haind/open-multi-agent-file-write-dangling-symlink-escape"
},
{
"source": "disclosure@vulncheck.com",
"url": "https://www.vulncheck.com/advisories/open-multi-agent-1.5.0-through-1.21.2-sandbox-escape-via-file-write-dangling-symlink"
}
],
"sourceIdentifier": "disclosure@vulncheck.com",
"vulnStatus": "Received",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-59"
}
],
"source": "disclosure@vulncheck.com",
"type": "Primary"
}
]
}
}
}
}
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…