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.
Affected products
dkfz: nnu-net
References2
- github.com/MIC-DKFZ/nnUNet/security/advisories/GHSA-63mx-j37w-g… ExploitMitigationVendor Advisory
- github.com/MIC-DKFZ/nnUNet/security/advisories/GHSA-63mx-j37w-g… ExploitMitigationVendor Advisory
Metrics
- CVSS 3.1
-
7.2
HIGH
Score source: CNA
CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N - EPSS — exploit probability
- 0% percentile: 22 · as of 14 November 2026
- CWE
- CWE-74
Could this be exploited in your environment?
A patch closes the known hole. A penetration test shows what an attacker can still reach — with proof.