CVE-2026-44246
Published: 12 May 2026
Summary
CVE-2026-44246 is a high-severity Injection (CWE-74) vulnerability in Dkfz Nnu-Net. Its CVSS base score is 7.2 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Exploit Public-Facing Application (T1190); ranked at the 18.5th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog; a public proof-of-concept is referenced.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the LLM/Generative AI Risks risk domain.
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-29841
Vulnerability details
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…
more
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.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- LLM/Generative AI Risks
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: claude
Related Threats
MITRE ATT&CK Enterprise TechniquesAI
Why these techniques?
Vulnerability enables direct exploitation of a public-facing GitHub workflow (issues.opened trigger) via untrusted input injection into an agentic action that executes commands through gh and Claude.
CVEs Like This One
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Developer assessments and testing (including injection-focused techniques) identify improper neutralization of special elements, and the verifiable flaw remediation corrects them pre-deployment.
Identifies indicators of injection attacks (command, SQL, LDAP, etc.) via anomaly and attack monitoring.