CVE-2026-81096

ToolUniverse ran caller-supplied Python inside a sandbox that could be escaped, on a server that required no authentication. The executor behind the python_code_executor tool, in python_executor_tool.py, inspected the submitted source for a denied list of attribute names and calls but left the attribute-lookup builtins available and did not stop a dunder attribute reached through a string lookup or through a module already permitted, so a caller could walk from a literal's class to its base and enumerate subclasses to obtain a reference to the process and subprocess modules. A per-call argument also let the caller widen the import allow-list before the inspection ran. The HTTP and MCP servers in http_api_server.py and smcp_server.py bound to every interface with debugging enabled and no authentication, so any caller able to reach the port executed code as the server process. Version 1.3.0 adds bearer-token authentication, defaults the bind address to loopback, and hardens the attribute checks.

CVSS v3 10.0 CRITICAL

10.0^/10

CVSS v3 : CRITICAL

Vector :

Exploitability : 3.9 / Impact : 6.0

Attack Vector NETWORK

Attack Complexity LOW

Privileges Required NONE

User Interaction NONE

Confidentiality Impact HIGH

Integrity Impact HIGH

Availability Impact HIGH

Scope CHANGED

References

Link	Resource
https://github.com/mims-harvard/ToolUniverse
https://github.com/mims-harvard/ToolUniverse/pull/251
https://github.com/mims-harvard/ToolUniverse/security/advisories/GHSA-pxwq-22vf-87fm
https://www.vulncheck.com/advisories/tooluniverse-through-1.2.6-unauthenticated-remote-code-execution-via-python-code-executor-sandbox-escape

Configurations

No configuration.

History

No history.

Information

Published : 2026-08-27 17:20

Updated : 2026-08-27 20:18

NVD link : CVE-2026-81096

Mitre link : CVE-2026-81096

CVE.ORG link : CVE-2026-81096

JSON object : View

Products Affected

No product.

CWE

CWE-94

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

{"id": "CVE-2026-81096", "cveTags": [], "metrics": {"ssvcV203": [{"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0", "ssvcData": {"id": "CVE-2026-81096", "role": "CISA Coordinator", "options": [{"exploitation": "none"}, {"automatable": "yes"}, {"technicalImpact": "total"}], "version": "2.0.3", "timestamp": "2026-08-27T18:13:07.150435Z"}}], "cvssMetricV31": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"scope": "CHANGED", "version": "3.1", "baseScore": 10.0, "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:H/I:H/A:H", "integrityImpact": "HIGH", "userInteraction": "NONE", "attackComplexity": "LOW", "availabilityImpact": "HIGH", "privilegesRequired": "NONE", "confidentialityImpact": "HIGH"}, "impactScore": 6.0, "exploitabilityScore": 3.9}], "cvssMetricV40": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "cvssData": {"Safety": "NOT_DEFINED", "version": "4.0", "Recovery": "NOT_DEFINED", "baseScore": 9.3, "Automatable": "NOT_DEFINED", "attackVector": "NETWORK", "baseSeverity": "CRITICAL", "valueDensity": "NOT_DEFINED", "vectorString": "CVSS:4.0/AV:N/AC:L/AT:N/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": "NONE", "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": "disclosure@vulncheck.com", "affectedData": [{"repo": "https://github.com/mims-harvard/ToolUniverse", "vendor": "mims-harvard", "product": "ToolUniverse", "versions": [{"status": "affected", "version": "0", "versionType": "semver", "lessThanOrEqual": "1.2.6"}], "packageURL": "pkg:pypi/tooluniverse", "collectionURL": "https://github.com/mims-harvard/ToolUniverse", "defaultStatus": "unaffected"}]}], "published": "2026-08-27T17:20:51.950", "references": [{"url": "https://github.com/mims-harvard/ToolUniverse", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/mims-harvard/ToolUniverse/pull/251", "source": "disclosure@vulncheck.com"}, {"url": "https://github.com/mims-harvard/ToolUniverse/security/advisories/GHSA-pxwq-22vf-87fm", "source": "disclosure@vulncheck.com"}, {"url": "https://www.vulncheck.com/advisories/tooluniverse-through-1.2.6-unauthenticated-remote-code-execution-via-python-code-executor-sandbox-escape", "source": "disclosure@vulncheck.com"}], "vulnStatus": "Received", "weaknesses": [{"type": "Secondary", "source": "disclosure@vulncheck.com", "description": [{"lang": "en", "value": "CWE-94"}]}], "descriptions": [{"lang": "en", "value": "ToolUniverse ran caller-supplied Python inside a sandbox that could be escaped, on a server that required no authentication. The executor behind the python_code_executor tool, in python_executor_tool.py, inspected the submitted source for a denied list of attribute names and calls but left the attribute-lookup builtins available and did not stop a dunder attribute reached through a string lookup or through a module already permitted, so a caller could walk from a literal's class to its base and enumerate subclasses to obtain a reference to the process and subprocess modules. A per-call argument also let the caller widen the import allow-list before the inspection ran. The HTTP and MCP servers in http_api_server.py and smcp_server.py bound to every interface with debugging enabled and no authentication, so any caller able to reach the port executed code as the server process. Version 1.3.0 adds bearer-token authentication, defaults the bind address to loopback, and hardens the attribute checks."}], "lastModified": "2026-08-27T20:18:49.567", "sourceIdentifier": "disclosure@vulncheck.com"}