CVE-2026-29791
Official description Straight from the sourceThe vendor's or NVD's own wording, published unedited. Authoritative, but often terse — it says what broke, rarely what to do.
NVD · uneditedAgentgateway 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.
Technical summary Written by usOur analysis, written from the advisory, the CVSS vector and the affected-version data. It adds context the advisory leaves out, and never invents facts that are not in the source.
dbcve analysis · high confidenceAgentgateway fails to sanitize input path, query, and header values when converting MCP tools/call requests to OpenAPI requests. This lack of input validation could allow injection attacks or manipulation of HTTP requests during the conversion process.
Verify against the referenced sources before acting — the references below are authoritative for this CVE, this summary is not.
Affected products & versions What the vendor confirmedThe version ranges the vendor confirmed as vulnerable. If your version sits inside a range here, treat yourself as exposed until you have upgraded.
NVD · CPE data< 0.12.0CVSS breakdown How the score is builtThe industry scoring standard. It rates how the flaw is reached, what it takes to exploit, and what an attacker gains — the score is derived from those, not the other way round.
From the vector- Attack vector
- Network
- Complexity
- Low
- Privileges
- None
- User interaction
- None
- Scope
- Unchanged
- Confidentiality
- Low
- Integrity
- Low
- Availability
- None
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:L/I:L/A:N
Am I affected? How to checkSteps we derive from the advisory and the affected-version data, so you can decide whether this CVE reaches your setup. They are a guide, not a scan — your own configuration is the authority.
dbcve checksWork through these to decide whether this CVE applies to you.
-
Check installed Agentgateway versionRun 'pip show agentgateway' or check your package manager for the installed version. If using a container, check the image tag or inspect the container metadata.Affected if The installed version is below 0.12.0
-
Identify if MCP tool conversions are in useReview your Agentgateway configuration or logs for any MCP (Model Context Protocol) tool or call request patterns. Look for endpoints or routes that handle MCP-to-OpenAPI conversions.Affected if MCP tool/call requests are being processed by the gateway
-
Inspect input validation configurationExamine the Agentgateway configuration files (typically in /etc/agentgateway/ or the project config directory) for any input validation, sanitization, or filtering settings related to path, query, or header parameters.Affected if No input validation is explicitly configured for MCP conversions
-
Check for suspicious request patterns in logsReview gateway access and error logs for unusual patterns in path, query, or header values that may indicate injection attempts during MCP conversions.Affected if Log entries show unexpected or malformed input values in MCP-related requests
-
Verify gateway exposureDetermine if the Agentgateway service is exposed to untrusted inputs. Check network configuration, firewall rules, and whether the gateway accepts requests from external or untrusted sources.Affected if The gateway accepts direct external input without an upstream filtering layer
You are affected if Agentgateway version is below 0.12.0 and the gateway processes MCP tool/call requests from untrusted or external sources.
Generated from the published advisory. Verify against your own configuration.
Remediation Closing itWhat it takes to close this. Where a vendor fix exists we point at it; where none exists we say so plainly, and can build one. Effort estimates are scoped from the advisory, not from your codebase.
dbcve · scoped0.12.0
Upgrade to version 0.12.0 or later, which includes the patch for proper input sanitization during MCP to OpenAPI conversion.
version 0.12.0
- Upgrade Agentgateway to version 0.12.0 or later by updating your installation
- Verify the upgrade was successful by checking the installed version
- Test that MCP tool to OpenAPI request conversion works correctly with sanitized inputs
- Confirm path, query, and header values are now properly validated during conversion
Generated from the published advisory — verify against the referenced sources before acting.
- Consultation2.0 h
- Implementation4.0 h
- Testing4.0 h
- Review / QA2.0 h
An estimate, not a bill — we confirm scope with you before any work starts. Need it this week? Rush from $3,328.
Scan for this in your stack
Free · runs locallyCheck whether your project pulls in CVE-2026-29791 — or any other known-vulnerable package — straight from your lock files. Free and open source; it runs locally and uploads nothing.
References Go to the primary sourcePrimary sources — vendor advisories, patches and trackers. Where our summary and a reference disagree, the reference wins.
Primary sourcesPractitioner notes
ContributedPeer-ranked notes from engineers who’ve handled CVE-2026-29791 in production — separate from our analysis above.
The advisory tells you what broke. It rarely tells you what actually worked. If you’ve dealt with this one, that detail is what the next engineer is searching for.
- The version that genuinely resolved it — not the one the vendor claimed
- A config change or rule that shut the vector down
- A gotcha in the upgrade path that cost you an afternoon
No notes yet
Be the first to add a field note for this CVE — a mitigation you’ve verified, a version caveat, or a link to a working fix. Sign in above to contribute.
A place for practitioners to share what actually worked: a mitigation you’ve tested, a configuration change, a version- or environment-specific caveat, or a link to a verified patch. The most useful notes rise to the top as peers upvote them, so the signal stays high.
- Verified mitigations, workarounds, and config changes
- Version or environment caveats, and links to real fixes
- No weaponised exploit code, or anything meant to cause harm
- No spam, self-promotion, credentials, or personal data