nnU-Net: Agentic workflow injection in `.github/workflows/issue-triage.yml` of `MIC-DKFZ/nnUNet`

nnU-Net is a semantic segmentation framework that automatically adapts its pipeline to a dataset. Prior to 2.4.1, the nnU-Net Issue Triage workflow in .github/workflows/issue-triage.yml is vulnerable to Agentic Workflow Injection. The workflow sets allowed_non_write_users: ${{ github.event.issue.user.login }}, which means any logged-in GitHub user who opens an issue can reach this agentic workflow with attacker-controlled content. Untrusted issue title and body content are embedded directly into the prompt of anthropics/claude-code-action, and the workflow then runs a command-capable Claude agent with permission to comment on and relabel the current issue via gh. Because this workflow is triggered automatically on issues.opened, an external attacker can submit a crafted issue that steers the agent beyond its intended issue-triage purpose and influences authenticated issue actions. This vulnerability is fixed in 2.4.1.

Problem type

CWE-1427:

Affected products

MIC-DKFZ

nnUNet

< 2.4.1 - AFFECTED

References

https://github.com/MIC-DKFZ/nnUNet/security/advisories/GHSA-63mx-j37w-gh59

https://github.com/MIC-DKFZ/nnUNet/security/advisories/GHSA-63mx-j37w-gh59

x_refsource_CONFIRM

JSON source

https://cveawg.mitre.org/api/cve/CVE-2026-44246

Click to expand

{
  "dataType": "CVE_RECORD",
  "dataVersion": "5.2",
  "cveMetadata": {
    "cveId": "CVE-2026-44246",
    "assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
    "assignerShortName": "GitHub_M",
    "dateUpdated": "2026-05-12T20:41:32.162Z",
    "dateReserved": "2026-05-05T16:33:55.844Z",
    "datePublished": "2026-05-12T20:41:32.162Z",
    "state": "PUBLISHED"
  },
  "containers": {
    "cna": {
      "providerMetadata": {
        "orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
        "shortName": "GitHub_M",
        "dateUpdated": "2026-05-12T20:41:32.162Z"
      },
      "title": "nnU-Net: Agentic workflow injection in `.github/workflows/issue-triage.yml` of `MIC-DKFZ/nnUNet`",
      "descriptions": [
        {
          "lang": "en",
          "value": "nnU-Net is a semantic segmentation framework that automatically adapts its pipeline to a dataset. Prior to 2.4.1, the nnU-Net Issue Triage workflow in .github/workflows/issue-triage.yml is vulnerable to Agentic Workflow Injection. The workflow sets allowed_non_write_users: ${{ github.event.issue.user.login }}, which means any logged-in GitHub user who opens an issue can reach this agentic workflow with attacker-controlled content. Untrusted issue title and body content are embedded directly into the prompt of anthropics/claude-code-action, and the workflow then runs a command-capable Claude agent with permission to comment on and relabel the current issue via gh. Because this workflow is triggered automatically on issues.opened, an external attacker can submit a crafted issue that steers the agent beyond its intended issue-triage purpose and influences authenticated issue actions. This vulnerability is fixed in 2.4.1."
        }
      ],
      "affected": [
        {
          "vendor": "MIC-DKFZ",
          "product": "nnUNet",
          "versions": [
            {
              "version": "< 2.4.1",
              "status": "affected"
            }
          ]
        }
      ],
      "problemTypes": [
        {
          "descriptions": [
            {
              "lang": "en",
              "description": "CWE-1427:",
              "cweId": "CWE-1427",
              "type": "CWE"
            }
          ]
        }
      ],
      "references": [
        {
          "url": "https://github.com/MIC-DKFZ/nnUNet/security/advisories/GHSA-63mx-j37w-gh59",
          "name": "https://github.com/MIC-DKFZ/nnUNet/security/advisories/GHSA-63mx-j37w-gh59",
          "tags": [
            "x_refsource_CONFIRM"
          ]
        }
      ],
      "metrics": [
        {
          "cvssV3_1": {
            "version": "3.1",
            "vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N",
            "attackVector": "NETWORK",
            "attackComplexity": "LOW",
            "privilegesRequired": "NONE",
            "userInteraction": "NONE",
            "scope": "CHANGED",
            "confidentialityImpact": "LOW",
            "integrityImpact": "LOW",
            "availabilityImpact": "NONE",
            "baseScore": 7.2,
            "baseSeverity": "HIGH"
          }
        }
      ]
    }
  }
}