CVE-2026-44246
nnU-Net: Agentic workflow injection in .github/workflows/issue-triage.yml of MIC-DKFZ/nnUNet
- Published
- May 12, 2026
- Updated
- May 13, 2026
- Assigning CNA
- GitHub_M
- Evidence observed
- Sep 7, 2026
Primary CVSS
nvd · CVSS 3.1
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:NLow · next 30 days
- Percentile
- 15.7%
- Model date
- Sep 21, 2026
EPSS is a statistical estimate, not a certainty or a measure of impact. Combine it with CVSS, KEV status, exposure and your environment.
Summary
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.
Sources
2- gha-lab-733c168b88Research
Reproduces CVE-2026-44246, a prompt injection vulnerability in nnU-Net's GitHub Actions triage agent, demonstrating how issue content is inlined into AI prompts.
- agentic-workflow-injectionDetection
Reproducible vulnerable and fixed GitHub Actions fixtures for agentic workflow injection (CVE-2026-44246), with measured detector coverage and mitigation guidance.
Responsible use
Use vulnerability information only on systems you own or are authorized to test. Kitploit links to public research metadata and does not store exploit code or malicious payloads.