Vulnerability-Lookup

GHSA-V2X6-WWFW-R2RQ

Vulnerability from github – Published: 2026-03-05 01:02 – Updated: 2026-03-06 22:51

Summary

Agentgateway is missing parameter sanitization in MCP to OpenAPI conversion

Details

Summary

When converting MCP tools/call request to OpenAPI request, input path, query, and header values are not sanitized.

Details

When using the MCP to OpenAPI feature, the proxy lacks proper sanitization of input parameters in the MCP call, allowing: * Injection of additional path or query parameters. * Injection of additional headers.

Impacted Versions

This vulnerability is fixed in Agentgateway v0.12.0+. Users on older versions are recommended to upgrade to v0.12.0+.

This feature only impacts usage of the MCP to OpenAPI feature

Credits

Agentgateway extends its thanks to @spacewander for the report!

Severity

4.9 (Medium)


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

Show details on source website

JSON

To clipboard

{
  "affected": [
    {
      "package": {
        "ecosystem": "Go",
        "name": "github.com/agentgateway/agentgateway"
      },
      "ranges": [
        {
          "events": [
            {
              "introduced": "0"
            },
            {
              "fixed": "0.12.0"
            }
          ],
          "type": "ECOSYSTEM"
        }
      ]
    }
  ],
  "aliases": [
    "CVE-2026-29791"
  ],
  "database_specific": {
    "cwe_ids": [
      "CWE-20"
    ],
    "github_reviewed": true,
    "github_reviewed_at": "2026-03-05T01:02:47Z",
    "nvd_published_at": "2026-03-06T21:16:15Z",
    "severity": "MODERATE"
  },
  "details": "### Summary\n\nWhen converting MCP `tools/call` request to OpenAPI request, input path, query, and header values are not sanitized.\n\n### Details\n\nWhen using the [MCP to OpenAPI](https://agentgateway.dev/docs/standalone/latest/mcp/connect/openapi/) feature, the proxy lacks proper sanitization of input parameters in the MCP call, allowing:\n* Injection of additional path or query parameters.\n* Injection of additional headers.\n\n### Impacted Versions\n\nThis vulnerability is fixed in Agentgateway v0.12.0+. Users on older versions are recommended to upgrade to v0.12.0+.\n\nThis feature only impacts usage of the [MCP to OpenAPI](https://agentgateway.dev/docs/standalone/latest/mcp/connect/openapi/) feature\n\n### Credits\n\nAgentgateway extends its thanks to @spacewander for the report!",
  "id": "GHSA-v2x6-wwfw-r2rq",
  "modified": "2026-03-06T22:51:46Z",
  "published": "2026-03-05T01:02:47Z",
  "references": [
    {
      "type": "WEB",
      "url": "https://github.com/agentgateway/agentgateway/security/advisories/GHSA-v2x6-wwfw-r2rq"
    },
    {
      "type": "ADVISORY",
      "url": "https://nvd.nist.gov/vuln/detail/CVE-2026-29791"
    },
    {
      "type": "WEB",
      "url": "https://github.com/agentgateway/agentgateway/commit/9a5287569d892e77a8be8c3bb7bf3d7744244274"
    },
    {
      "type": "PACKAGE",
      "url": "https://github.com/agentgateway/agentgateway"
    }
  ],
  "schema_version": "1.4.0",
  "severity": [
    {
      "score": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:L/I:L/A:N",
      "type": "CVSS_V3"
    }
  ],
  "summary": "Agentgateway is missing parameter sanitization in MCP to OpenAPI conversion"
}

CVE-2026-29791 (GCVE-0-2026-29791)

Vulnerability from cvelistv5 – Published: 2026-03-06 20:39 – Updated: 2026-03-09 20:54

Title

Agentgateway: Missing parameter sanitization in MCP to OpenAPI conversion

Summary

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.

Severity

4.9 (Medium)


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

SSVC

Exploitation: none Automatable: no Technical Impact: partial

CISA Coordinator · CISA-ADP (v2.0.3)

Decision recorded 2026-03-09 20:50 UTC

CWE

CWE-20 - Improper Input Validation

Assigner

GitHub_M mitre root

References

1 reference

URL	Tags
https://github.com/agentgateway/agentgateway/secu…	x_refsource_CONFIRM

Impacted products

1 product

Vendor	Product	Version
agentgateway	agentgateway	Affected: < 0.12.0

Show details on NVD website

JSON

To clipboard

{
  "containers": {
    "adp": [
      {
        "metrics": [
          {
            "other": {
              "content": {
                "id": "CVE-2026-29791",
                "options": [
                  {
                    "Exploitation": "none"
                  },
                  {
                    "Automatable": "no"
                  },
                  {
                    "Technical Impact": "partial"
                  }
                ],
                "role": "CISA Coordinator",
                "timestamp": "2026-03-09T20:50:18.880504Z",
                "version": "2.0.3"
              },
              "type": "ssvc"
            }
          }
        ],
        "providerMetadata": {
          "dateUpdated": "2026-03-09T20:54:30.319Z",
          "orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
          "shortName": "CISA-ADP"
        },
        "title": "CISA ADP Vulnrichment"
      }
    ],
    "cna": {
      "affected": [
        {
          "product": "agentgateway",
          "vendor": "agentgateway",
          "versions": [
            {
              "status": "affected",
              "version": "\u003c 0.12.0"
            }
          ]
        }
      ],
      "descriptions": [
        {
          "lang": "en",
          "value": "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."
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "attackComplexity": "HIGH",
            "attackVector": "NETWORK",
            "availabilityImpact": "NONE",
            "baseScore": 4.9,
            "baseSeverity": "MEDIUM",
            "confidentialityImpact": "LOW",
            "integrityImpact": "LOW",
            "privilegesRequired": "LOW",
            "scope": "CHANGED",
            "userInteraction": "NONE",
            "vectorString": "CVSS:3.1/AV:N/AC:H/PR:L/UI:N/S:C/C:L/I:L/A:N",
            "version": "3.1"
          }
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "cweId": "CWE-20",
              "description": "CWE-20: Improper Input Validation",
              "lang": "en",
              "type": "CWE"
            }
          ]
        }
      ],
      "providerMetadata": {
        "dateUpdated": "2026-03-06T20:39:40.852Z",
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M"
      },
      "references": [
        {
          "name": "https://github.com/agentgateway/agentgateway/security/advisories/GHSA-v2x6-wwfw-r2rq",
          "tags": [
            "x_refsource_CONFIRM"
          ],
          "url": "https://github.com/agentgateway/agentgateway/security/advisories/GHSA-v2x6-wwfw-r2rq"
        }
      ],
      "source": {
        "advisory": "GHSA-v2x6-wwfw-r2rq",
        "discovery": "UNKNOWN"
      },
      "title": "Agentgateway: Missing parameter sanitization in MCP to OpenAPI conversion"
    }
  },
  "cveMetadata": {
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "cveId": "CVE-2026-29791",
    "datePublished": "2026-03-06T20:39:40.852Z",
    "dateReserved": "2026-03-04T16:26:02.900Z",
    "dateUpdated": "2026-03-09T20:54:30.319Z",
    "state": "PUBLISHED"
  },
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2"
}

Sightings

Author	Source	Type	Date	Other

Nomenclature

Seen: The vulnerability was mentioned, discussed, or observed by the user.
Confirmed: The vulnerability has been validated from an analyst's perspective.
Published Proof of Concept: A public proof of concept is available for this vulnerability.
Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
Not confirmed: The user expressed doubt about the validity of the vulnerability.
Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.

Detection rules are retrieved from Rulezet.

The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base model, served locally by ML-Gateway. They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.

Related by attack behaviour

Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.

Action not permitted

GHSA-V2X6-WWFW-R2RQ

Summary

Details

Impacted Versions

Credits

CVE-2026-29791 (GCVE-0-2026-29791)

Tags

Sightings

Nomenclature

Related by attack behaviour