CVE-2026-47751 — claude-code-action
Fix: anthropics/claude-code-action@9ddce40CVE-2026-47751 is a OS Command Injection vulnerability in anthropics/claude-code-action. A fix is available for anthropics/claude-code-action — see the affected versions and patch details below.
Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration
Exploitation Status
No confirmed exploitation observed yet
- CISA assesses this as automatable — exploitation doesn’t require manual, per-target effort, which raises the odds of mass scanning and opportunistic attacks.
- A successful exploit gives an attacker total control of the affected component, not partial access.
- CISA’s own triage has not observed active exploitation or public proof-of-concept code for this CVE as of its last assessment.
Exploitation and automatability from CISA’s SSVC triage for CVE-2026-47751.
EPSS Exploitation Probability
Probability of exploitation in the next 30 days, from FIRST.org EPSS.
Real-World Exposure
anthropics/claude-code-actionReal-time download stats are indexed for npm and PyPI packages. This vulnerability affects GitHub Actions packages — download data is not available via public APIs for these ecosystems.
Description
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 malicious .mcp.json file to achieve arbitrary code execution on the GitHub Actions runner. This could lead to exfiltration of secrets available to the workflow (such as API keys and tokens) when a privileged user triggered the Claude action on the PR. Exploiting this required the ability to open a pull request against a repository using the claude-code-action and a privileged user or automatic trigger to invoke the action on that PR.
Users pinned to a vulnerable version of claude-code-action are advised to update to the latest version. Users referencing anthropics/claude-code-action@v1, anthropics/claude-code-action@beta, anthropics/claude-code-action@main, or other non-pinned tags will have received this fix already
Claude Code thanks hackerone.com/reptou for reporting this issue.
Affected Packages
| Ecosystem | Package | Vulnerable range | Fix |
|---|---|---|---|
| 📦GitHub Actions | anthropics/claude-code-action | all versions | 1.0.74 |
Detection & mitigation playbook
Open-source dependencyDetect
Scan your dependency tree (package-lock.json, pnpm-lock.yaml, requirements.txt, go.sum, etc.) for anthropics/claude-code-action, including transitive dependencies — a direct dependency you never call can still pull in a vulnerable version.
Fix
Update anthropics/claude-code-action to 1.0.74 or later, then make sure no transitive (indirect) dependency still pins the vulnerable range — O3 confirms CVE-2026-47751 is resolved across your whole dependency graph.
Workarounds
Stop passing untrusted input into the interpreter or shell: call the affected binary with an argument array rather than a composed command string, reject anything outside a strict allowlist of expected values, and run the component under an account that cannot reach beyond the work it legitimately does.
Frequently Asked Questions
Is CVE-2026-47751 in your dependencies?
Find it across GitHub Actions, including transitive dependencies.