MediumVulnerability
CVE-2026-29791: Agentgateway input validation flaw in MCP tools/call to OpenAPI conversion
- Source
- NVD(opens in a new tab)
- Identifier
- CVE-2026-29791
- Published
- Record updated
- Affected
- github.com/agentgateway/agentgateway < 0.12.0
- Fixed in
- 0.12.0
- released February 9, 2026, 25 days before disclosure
- Known exploitation
- Not listed in the CISA Known Exploited Vulnerabilities catalog at the last check.
- EPSS
- 0.2%
Summary
CVE-2026-29791 affects Agentgateway, an open source data plane for agentic AI connectivity, prior to version 0.12.0. When converting an MCP tools/call request to an OpenAPI request, input path, query, and header values are not sanitized, which is classified as CWE-20 Improper Input Validation. The NVD assessment has not yet been provided.
Mitigation
This issue has been patched in version 0.12.0.
Topics
Related items
- MediumCVE-2026-121936: easyVoice server-side request forgery through openaiBaseUrl in /api/v1/ttsSimilar attack · NVD/CVE Database
- MediumCVE-2026-118628: MLflow get-artifacts server-side request forgery information disclosureSimilar attack · NVD/CVE Database
- HighCVE-2026-118625: MLflow Tracking Server privilege escalation via get_endpointsSimilar attack · NVD/CVE Database
- InfoWhen trust becomes the payload: Inside the threats, etc quarterly reportSimilar attack · Elastic Security Labs
- MediumCritical Langflow flaws enable authentication bypass and RCESimilar attack · CSO Online