agentic-workflow-injection

Agentic workflow injection: fixtures and a coverage comparison Reproducible vulnerable/fixed fixtures for the class of bug published as CVE-2026-44246 nnU-Net, agentic workflow injection, CVSS 7.2, CWE-1427, plus the measured output of three detectors against them. It exists because there was...

Exploit for Injection in Dkfz Nnu-Net

Agentic workflow injection: fixtures and a coverage comparison...

CVE-2026-47751

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

CVE-2026-47751

CVE-2026-47751 affects Claude Code Action prior to version 1.0.74. Due to the action checking out attacker-controlled PR head branches, reading .mcp.json from the working directory, and unconditionally enabling all MCP servers via enableAllProjectMcpServers, an attacker could trigger arbitrary co...

EUVD-2026-44952

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

CVE-2026-47751 Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

CVE-2026-47751

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

CVE-2026-47751 Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

CVE-2026-47751 Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

CVE-2026-47751: Improper Neutralization of Special Elements used in an OS Command

Claude Code Action is a general-purpose GitHub action that runs Claude Code on GitHub pull requests and issues. Prior to 1.0.74, because the action checked out attacker-controlled pull request head branches, read .mcp.json from the working directory via default setting sources, and unconditionall...

Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration

Due to the combination of checking out PR head branches attacker-controlled, reading .mcp.json from the working directory via default setting sources, and unconditionally enabling all project MCP servers via enableAllProjectMcpServers, it was possible for an attacker who opened a PR containing a...

GHSA-8Q5R-MMJF-575Q Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration

Due to the combination of checking out PR head branches attacker-controlled, reading .mcp.json from the working directory via default setting sources, and unconditionally enabling all project MCP servers via enableAllProjectMcpServers, it was possible for an attacker who opened a PR containing a...

PT-2026-48540

Due to the combination of checking out PR head branches attacker-controlled, reading .mcp.json from the working directory via default setting sources, and unconditionally enabling all project MCP servers via enableAllProjectMcpServers, it was possible for an attacker who opened a PR containing a...

Securing CI/CD in an agentic world: Claude Code Github action case

Microsoft Threat Intelligence discovered that Anthropic's Claude Code GitHub Action could expose CI/CD workflow secrets when AI agents process untrusted GitHub content, including issue bodies, pull request descriptions, and comments. We found that while Claude Code Action supported environment...

Claude Code GitHub Action Flaw Let One Malicious Issue Hijack Repositories

A security researcher found a flaw in Anthropic's Claude Code GitHub Action that let an attacker take over vulnerable public repositories running it, with nothing more than a single opened GitHub issue. Because Anthropic's own action repo used the same workflow, a working attack could have pushed...

EUVD-2026-29841

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 allowednonwriteusers: $...

CVE-2026-44246

The CVE concerns nnU-Net (MIC-DKFZ/nnUNet) before version 2.4.1. The issue lies in the nnU-Net Issue Triage workflow at .github/workflows/issue-triage.yml, which sets allowed_non_write_users: ${{ github.event.issue.user.login }}. This allows any logged-in GitHub user opening an issue to reach an ...

CVE-2026-44246: Improper Neutralization of Special Elements in Output Used by a Downstream Component

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 allowednonwriteusers: $...

PT-2026-40433

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: $...

MAL-2025-1057 Malicious code in action-npm-publish (npm)

--- -= Per source details. Do not edit below this line.=- Source: ghsa-malware 048a0cf0cca0b18a85e69e831d1c26f1bec7888c3f5e1865bd185b3470fb9e2c Any computer that has this package installed or running should be considered fully compromised. All secrets and keys stored on that computer should be...