CVE-2026-25481

Langroid is a framework for building large-language-model-powered applications. Prior to version 0.59.32, there is a bypass to the fix for CVE-2025-46724. TableChatAgent can call pandas_eval tool to evaluate the expression. There is a WAF in langroid/utils/pandas_utils.py introduced to block code injection CVE-2025-46724. However it can be bypassed due to _literal_ok() returning False instead of raising UnsafeCommandError on invalid input, combined with unrestricted access to dangerous dunder attributes (__init__, __globals__, __builtins__). This allows chaining whitelisted DataFrame methods to leak the eval builtin and execute arbitrary code. This issue has been patched in version 0.59.32.

CVSS v3 9.6 CRITICAL

9.6^/10

CVSS v3 : CRITICAL

Vector :

Exploitability : 2.8 / Impact : 6.0

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction REQUIRED

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope CHANGED

References

Link	Resource
https://github.com/langroid/langroid/commit/30abbc1a854dee22fbd2f8b2f575dfdabdb603ea	Patch
https://github.com/langroid/langroid/security/advisories/GHSA-jqq5-wc57-f8hj	Vendor Advisory
https://github.com/langroid/langroid/security/advisories/GHSA-x34r-63hx-w57f	Exploit Vendor Advisory

Configurations

Configuration 1 (hide)

cpe:2.3:a:langroid:langroid:*:*:*:*:*:*:*:*

History

No history.

Information

Published : 2026-02-04 20:16

Updated : 2026-06-17 10:24

NVD link : CVE-2026-25481

Mitre link : CVE-2026-25481

CVE.ORG link : CVE-2026-25481

JSON object : View

Products Affected

langroid

langroid

CWE

CWE-94

Improper Control of Generation of Code ('Code Injection')

{"id": "CVE-2026-25481", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-25481", "role": "CISA Coordinator", "options": [{"exploitation": "poc"}, {"automatable": "yes"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-02-04T20:39:55.136196Z"}}], "cvssMetricV31": [{"type": "Primary", "source": "nvd@nist.gov", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 9.6, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:R/S:C/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "REQUIRED", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 6.0, "exploitabilityScore": 2.8}], "cvssMetricV40": [{"type": "Secondary", "source": "security-advisories@github.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 9.4, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/PR:N/UI:P/VC:H/VI:H/VA:H/SC:H/SI:H/SA:H/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": "PASSIVE", "attackComplexity": "LOW", "attackRequirements": "NONE", "privilegesRequired": "NONE", "subIntegrityImpact": "HIGH", "vulnIntegrityImpact": "HIGH", "integrityRequirement": "NOT_DEFINED", "modifiedAttackVector": "NOT_DEFINED", "subAvailabilityImpact": "HIGH", "vulnAvailabilityImpact": "HIGH", "availabilityRequirement": "NOT_DEFINED", "modifiedUserInteraction": "NOT_DEFINED", "modifiedAttackComplexity": "NOT_DEFINED", "subConfidentialityImpact": "HIGH", "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": "security-advisories@github.com", "affectedData": [{"vendor": "langroid", "product": "langroid", "versions": [{"status": "affected", "version": "< 0.59.32"}]}]}], "published": "2026-02-04T20:16:07.447", "references": [{"url": "https://github.com/langroid/langroid/commit/30abbc1a854dee22fbd2f8b2f575dfdabdb603ea", "tags": ["Patch"], "source": "security-advisories@github.com"}, {"url": "https://github.com/langroid/langroid/security/advisories/GHSA-jqq5-wc57-f8hj", "tags": ["Vendor Advisory"], "source": "security-advisories@github.com"}, {"url": "https://github.com/langroid/langroid/security/advisories/GHSA-x34r-63hx-w57f", "tags": ["Exploit", "Vendor Advisory"], "source": "security-advisories@github.com"}], "vulnStatus": "Analyzed", "weaknesses": [{"type": "Secondary", "source": "security-advisories@github.com", "description": [{"lang": "en", "value": "CWE-94"}]}], "descriptions": [{"lang": "en", "value": "Langroid is a framework for building large-language-model-powered applications. Prior to version 0.59.32, there is a bypass to the fix for CVE-2025-46724. TableChatAgent can call pandas_eval tool to evaluate the expression. There is a WAF in langroid/utils/pandas_utils.py introduced to block code injection CVE-2025-46724. However it can be bypassed due to _literal_ok() returning False instead of raising UnsafeCommandError on invalid input, combined with unrestricted access to dangerous dunder attributes (__init__, __globals__, __builtins__). This allows chaining whitelisted DataFrame methods to leak the eval builtin and execute arbitrary code. This issue has been patched in version 0.59.32."}, {"lang": "es", "value": "Langroid es un framework para construir aplicaciones impulsadas por modelos de lenguaje grandes. Antes de la versi\u00f3n 0.59.32, existe un bypass para la correcci\u00f3n de CVE-2025-46724. TableChatAgent puede llamar a la herramienta pandas_eval para evaluar la expresi\u00f3n. Existe un WAF en langroid/utils/pandas_utils.py introducido para bloquear la inyecci\u00f3n de c\u00f3digo CVE-2025-46724. Sin embargo, puede ser evadido debido a que _literal_ok() devuelve False en lugar de lanzar UnsafeCommandError en una entrada inv\u00e1lida, combinado con el acceso sin restricciones a atributos dunder peligrosos (__init__, __globals__, __builtins__). Esto permite encadenar m\u00e9todos de DataFrame en lista blanca para filtrar el builtin eval y ejecutar c\u00f3digo arbitrario. Este problema ha sido parcheado en la versi\u00f3n 0.59.32."}], "lastModified": "2026-06-17T10:24:42.560", "configurations": [{"nodes": [{"negate": false, "cpeMatch": [{"criteria": "cpe:2.3:a:langroid:langroid:*:*:*:*:*:*:*:*", "vulnerable": true, "matchCriteriaId": "D5E51268-4EEF-4AFB-A80B-DA57B3099F66", "versionEndExcluding": "0.59.32"}], "operator": "OR"}]}], "sourceIdentifier": "security-advisories@github.com"}