CVE-2026-44246 nnU-Net: Agentic workflow injection in `.github/workflows/issue-triage.yml` of `MIC-DKFZ/nnUNet`
- Published
- Updated
- Exploit status
- No public exploit known
- CISA SSVC
- Proof of concept public · automatable: yes · technical impact: partial
Description
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.
Upgrade path
2 packages: 1 fixed.
| Package | Affected | Fixed in | Status |
|---|---|---|---|
| dkfz nnu-net | < 2.4.1 | 2.4.1 | Fixed |
| MIC-DKFZ nnUNet | = < 2.4.1 | No fix listed | Versions listed |
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| MIC-DKFZ nnUNet | = < 2.4.1 | No fix listed |
| dkfz nnu-net | < 2.4.1 | 2.4.1 |
References
- https://github.com/MIC-DKFZ/nnUNet/security/advisories/GHSA-63mx-j37w-gh59 exploit mitigation vendor-advisory