CVE-2026-64651
The `@ai-sdk/harness-opencode` tool connects HarnessAgent to OpenCode through a sandboxed bridge. Prior to version 1.0.28, the tool relay authorizes requests from any process whose command line contains an allowed helper script path (`host-tool-mcp.mjs`). This allows untrusted code executing in the sandbox to invoke arbitrary host-exposed tools including secret lookups, deployment operations, and cloud API calls without a corresponding model-authorized tool-call event.
Leer descripción completaMostrar menos
Exploitation requires a Linux environment (the vulnerable fallback checks `process.platform === 'linux'` and reads `/proc`); an active harness session with one or more host-provided tools; and untrusted code executing in the sandbox (e.g. a malicious dependency, build script, or lifecycle hook) The fix in version 1.0.28 removes the process-path authorization fallback entirely. Relay requests are now only accepted after exact, short-lived, one-time authorization matching the tool name and input from a bridge-observed model event. Some workarounds are available. Do not run the OpenCode harness on untrusted repositories or with untrusted dependencies, and/or limit host-exposed tools to non-sensitive operations when working with untrusted code.
CVSS
- Versión: 4.0
- Vector: CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:L/VA:N/SC:H/SI:H/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
- Puntuación base: 6.3
Probabilidad de explotación (EPSS)
- Probabilidad de explotación en los próximos 30 días: 0.17%
- Percentil entre todas las CVEs puntuadas: 6
- Fecha de la puntuación: 6/10/2026
EPSS (Exploit Prediction Scoring System, de FIRST) estima la probabilidad de que una vulnerabilidad sea explotada en 30 días. Complementa a CVSS (impacto) y a CISA KEV (explotación confirmada).
Tecnologías afectadas (3)
⚠ Inferidas por IA a partir de la descripción — NVD aún no ha analizado esta CVE; no son CPE verificados.
CWE
- CWE-863
Referencias
JSON original (NVD)
Mostrar
{
"id": "CVE-2026-64651",
"cveTags": [],
"metrics": {
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-64651",
"role": "CISA Coordinator",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "partial"
}
],
"version": "2.0.3",
"timestamp": "2026-07-21T12:49:24.395782Z"
}
}
],
"cvssMetricV40": [
{
"type": "Secondary",
"source": "security-advisories@github.com",
"cvssData": {
"Safety": "NOT_DEFINED",
"version": "4.0",
"Recovery": "NOT_DEFINED",
"baseScore": 6.3,
"Automatable": "NOT_DEFINED",
"attackVector": "LOCAL",
"baseSeverity": "MEDIUM",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:L/AC:L/AT:N/PR:N/UI:N/VC:N/VI:L/VA:N/SC:H/SI:H/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",
"exploitMaturity": "NOT_DEFINED",
"providerUrgency": "NOT_DEFINED",
"userInteraction": "NONE",
"attackComplexity": "LOW",
"attackRequirements": "NONE",
"privilegesRequired": "NONE",
"subIntegrityImpact": "HIGH",
"vulnIntegrityImpact": "LOW",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"vulnAvailabilityImpact": "NONE",
"availabilityRequirement": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"subConfidentialityImpact": "HIGH",
"vulnConfidentialityImpact": "NONE",
"confidentialityRequirement": "NOT_DEFINED",
"modifiedAttackRequirements": "NOT_DEFINED",
"modifiedPrivilegesRequired": "NOT_DEFINED",
"modifiedSubIntegrityImpact": "NOT_DEFINED",
"modifiedVulnIntegrityImpact": "NOT_DEFINED",
"vulnerabilityResponseEffort": "NOT_DEFINED",
"modifiedSubAvailabilityImpact": "NOT_DEFINED",
"modifiedVulnAvailabilityImpact": "NOT_DEFINED",
"modifiedSubConfidentialityImpact": "NOT_DEFINED",
"modifiedVulnConfidentialityImpact": "NOT_DEFINED"
}
}
]
},
"affected": [
{
"source": "security-advisories@github.com",
"affectedData": [
{
"vendor": "vercel",
"product": "@ai-sdk/harness-opencode",
"versions": [
{
"status": "affected",
"version": "< 1.0.29"
}
]
}
]
}
],
"published": "2026-07-20T21:16:50.677",
"references": [
{
"url": "https://github.com/vercel/ai/pull/17105",
"source": "security-advisories@github.com"
},
{
"url": "https://github.com/vercel/ai/security/advisories/GHSA-g48p-5rr5-8rgq",
"source": "security-advisories@github.com"
}
],
"vulnStatus": "Deferred",
"weaknesses": [
{
"type": "Secondary",
"source": "security-advisories@github.com",
"description": [
{
"lang": "en",
"value": "CWE-863"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "The `@ai-sdk/harness-opencode` tool connects HarnessAgent to OpenCode through a sandboxed bridge. Prior to version 1.0.28, the tool relay authorizes requests from any process whose command line contains an allowed helper script path (`host-tool-mcp.mjs`). This allows untrusted code executing in the sandbox to invoke arbitrary host-exposed tools including secret lookups, deployment operations, and cloud API calls without a corresponding model-authorized tool-call event. Exploitation requires a Linux environment (the vulnerable fallback checks `process.platform === 'linux'` and reads `/proc`); an active harness session with one or more host-provided tools; and untrusted code executing in the sandbox (e.g. a malicious dependency, build script, or lifecycle hook) The fix in version 1.0.28 removes the process-path authorization fallback entirely. Relay requests are now only accepted after exact, short-lived, one-time authorization matching the tool name and input from a bridge-observed model event. Some workarounds are available. Do not run the OpenCode harness on untrusted repositories or with untrusted dependencies, and/or limit host-exposed tools to non-sensitive operations when working with untrusted code."
}
],
"lastModified": "2026-07-23T18:14:09.843",
"sourceIdentifier": "security-advisories@github.com"
}