CVE-2026-78379
Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards non_interactive_mode as a keyword argument through the batch tool. To remediate this issue, users should upgrade to version 0.8.5 or later.
CVSS
- Versión: 4.0
- Vector: CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/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
- Puntuación base: 9.2
Probabilidad de explotación (EPSS)
- Probabilidad de explotación en los próximos 30 días: 0.57%
- Percentil entre todas las CVEs puntuadas: 46
- 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).
🎯 Técnicas ATT&CK
Cómo se explota esta vulnerabilidad y qué consigue el atacante, en el lenguaje de MITRE ATT&CK.
- Explotación
T1190Exploit Public-Facing Applicationinitial access85 % - Impacto principal
T1059Command and Scripting Interpreterexecution90 % - Impacto secundario
T1548Abuse Elevation Control Mechanismprivilege escalation70 %
AV:N, AC:L, PR:N permite explotación remota sin autenticación (T1190). La ejecución arbitraria de código Python en el host del agente es el impacto primario (T1059). El bypass del gate de consentimiento humano implica elevación o asunción de privilegios no autorizados (T1548).
Inferido por nuestro agente de análisis a partir de la descripción oficial, el vector CVSS y la CWE, y comprobado por un supervisor. Puede contener errores.
🛡️ Mitigaciones ATT&CK que cubren estas técnicas
Tecnologías afectadas (1)
⚠ Inferidas por IA a partir de la descripción — NVD aún no ha analizado esta CVE; no son CPE verificados.
Referencias
JSON original (NVD)
Mostrar
{
"id": "CVE-2026-78379",
"cveTags": [],
"metrics": {
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-78379",
"role": "CISA Coordinator",
"options": [
{
"exploitation": "none"
},
{
"automatable": "no"
},
{
"technicalImpact": "total"
}
],
"version": "2.0.3",
"timestamp": "2026-08-25T19:19:45.557051Z"
}
}
],
"cvssMetricV31": [
{
"type": "Secondary",
"source": "ff89ba41-3aa1-4d27-914a-91399e9639e5",
"cvssData": {
"scope": "UNCHANGED",
"version": "3.1",
"baseScore": 8.1,
"attackVector": "NETWORK",
"baseSeverity": "HIGH",
"vectorString": "CVSS:3.1/AV:N/AC:H/PR:N/UI:N/S:U/C:H/I:H/A:H",
"integrityImpact": "HIGH",
"userInteraction": "NONE",
"attackComplexity": "HIGH",
"availabilityImpact": "HIGH",
"privilegesRequired": "NONE",
"confidentialityImpact": "HIGH"
},
"impactScore": 5.9,
"exploitabilityScore": 2.2
}
],
"cvssMetricV40": [
{
"type": "Secondary",
"source": "ff89ba41-3aa1-4d27-914a-91399e9639e5",
"cvssData": {
"Safety": "NOT_DEFINED",
"version": "4.0",
"Recovery": "NOT_DEFINED",
"baseScore": 9.2,
"Automatable": "NOT_DEFINED",
"attackVector": "NETWORK",
"baseSeverity": "CRITICAL",
"valueDensity": "NOT_DEFINED",
"vectorString": "CVSS:4.0/AV:N/AC:L/AT:P/PR:N/UI:N/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",
"exploitMaturity": "NOT_DEFINED",
"providerUrgency": "NOT_DEFINED",
"userInteraction": "NONE",
"attackComplexity": "LOW",
"attackRequirements": "PRESENT",
"privilegesRequired": "NONE",
"subIntegrityImpact": "NONE",
"vulnIntegrityImpact": "HIGH",
"integrityRequirement": "NOT_DEFINED",
"modifiedAttackVector": "NOT_DEFINED",
"subAvailabilityImpact": "NONE",
"vulnAvailabilityImpact": "HIGH",
"availabilityRequirement": "NOT_DEFINED",
"modifiedUserInteraction": "NOT_DEFINED",
"modifiedAttackComplexity": "NOT_DEFINED",
"subConfidentialityImpact": "NONE",
"vulnConfidentialityImpact": "HIGH",
"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": "ff89ba41-3aa1-4d27-914a-91399e9639e5",
"affectedData": [
{
"vendor": "Amazon",
"product": "strands-agents-tools",
"versions": [
{
"status": "affected",
"version": "0",
"lessThan": "0.8.5",
"versionType": "custom"
}
],
"defaultStatus": "unaffected"
}
]
}
],
"published": "2026-08-25T19:16:54.467",
"references": [
{
"url": "https://aws.amazon.com/security/security-bulletins/2026-089-aws/",
"source": "ff89ba41-3aa1-4d27-914a-91399e9639e5"
},
{
"url": "https://pypi.org/project/strands-agents-tools/0.8.5/",
"source": "ff89ba41-3aa1-4d27-914a-91399e9639e5"
}
],
"vulnStatus": "Awaiting Analysis",
"descriptions": [
{
"lang": "en",
"value": "Improper neutralization of input used for LLM prompting in the python_repl tool in Amazon Strands Agents Tools before 0.8.5 might allow remote actors to execute arbitrary Python code on the agent's host by bypassing the human consent gate, via a crafted prompt that forwards non_interactive_mode as a keyword argument through the batch tool. To remediate this issue, users should upgrade to version 0.8.5 or later."
}
],
"lastModified": "2026-08-26T16:45:12.020",
"sourceIdentifier": "ff89ba41-3aa1-4d27-914a-91399e9639e5"
}