Skip to content
Fencer Vulns
high 7.2

CVE-2026-44246 json

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

published 2026-05-12 5 mo ago modified 2026-10-26 13 d ago also EUVD-2026-29841

cvss
7.2
version 3.1, CNA
cisa kev
Not listed
not in CISA's catalog
epss
0.3%
EPSS 0.3% chance of exploitation in 30 days, percentile 21%
public exploits
0
none known

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.

Patch / fix

  • dkfz nnu-net 2.4.1

CISA SSVC

Exploitation
Proof of concept is public
Automatable
yes
Technical impact
partial
Assessed
5 mo ago

Exploit prediction

0.29% chance of exploitation in the next 30 days, higher than 21% of all scored CVEs (FIRST EPSS, 2026-11-08).

Exploits and checks

  • github.com https://github.com/MIC-DKFZ/nnUNet/security/advisories/GHSA-63mx-j37w-gh59 referenced PoC, tagged "exploit" by a source, unverified

CVSS scores

assigned by version score vector
CNA 3.1 7.2 CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:C/C:L/I:L/A:N

Affected products

  • MIC-DKFZ nnUNet

Classification

Weakness
  • CWE-1427 Improper Neutralization of Input Used for LLM Prompting
  • CWE-74 Improper Neutralization of Special Elements in Output Used by a Downstream Component

References

Sources

Fencer Vulns keeps one entry per vulnerability: the CVE id wins, then GHSA, and records that alias each other are merged, except that two CVEs always keep separate entries. The same data is available as JSON.