What is the CVSS score of CVE-2026-29791?

CVE-2026-29791 has a CVSS 3.1 base score of 4.9 (Medium). CVSS vector: CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:L/I:L/A:N. EPSS exploitation probability: 0.0%.

Which versions of Agentgateway are affected by CVE-2026-29791?

Organizations using or across any agent framework or environment. should be aware of moderate risk from CVE-2026-29791, a input validation vulnerability rated CVSS 4.9.. A patch is available.

How to fix or mitigate CVE-2026-29791?

Within 30 days: Identify affected systems running or across any agent framework or environment. and apply vendor patches as part of regular patch cycle. Monitor vendor channels for patch availability.

Agentgateway CVE-2026-29791

MEDIUM

Improper Input Validation (CWE-20)

2026-03-06 security-advisories@github.com

GHSA-v2x6-wwfw-r2rq

Information Disclosure Agentgateway

4.9

CVSS 3.1 · GitHub Advisory

Severity by source

GitHub Advisory PRIMARY

4.9 MEDIUM

AV:N/AC:H/PR:L/UI:N/S:C/C:L/I:L/A:N

Primary rating from GitHub Advisory · only source for this CVE.

CVSS VectorGitHub Advisory

CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:L/I:L/A:N

Attack Vector

Network

Attack Complexity

High

Privileges Required

Low

User Interaction

None

Scope

Changed

Confidentiality

Low

Integrity

Low

Availability

None

Lifecycle Timeline

Patch released

Mar 31, 2026 - 21:13 nvd

Patch available

Analysis Generated

Mar 12, 2026 - 22:06 vuln.today

CVE Published

Mar 06, 2026 - 21:16 nvd

MEDIUM 4.9

DescriptionGitHub Advisory

Agentgateway is an open source data plane for agentic AI connectivity within or across any agent framework or environment. Prior to version 0.12.0, when converting MCP tools/call request to OpenAPI request, input path, query, and header values are not sanitized. This issue has been patched in version 0.12.0.

AnalysisAI

Agentgateway versions prior to 0.12.0 fail to sanitize input parameters (path, query, and header values) when converting MCP tool requests to OpenAPI calls, allowing authenticated users to inject malicious data that could lead to unauthorized information disclosure or data modification. An attacker with valid credentials could exploit this input validation weakness to manipulate API requests across agent frameworks. No patch is currently available for affected deployments.

Technical ContextAI

This vulnerability (CWE-20: Improper Input Validation) affects Agentgateway is an open source data plane for agentic AI connectivity within or across any agent framework or environment.. Agentgateway is an open source data plane for agentic AI connectivity within or across any agent framework or environment. Prior to version 0.12.0, when converting MCP tools/call request to OpenAPI request, input path, query, and header values are not sanitized. This issue has been patched in version 0.12.0.