OS Command Injection in anthropics/claude-code-action (CVE-2026-47751)
Summary
OS command injection in anthropics/claude-code-action (CVE-2026-47751). Risk of unauthorized operations or information disclosure. Exploitable via enableAllProjectMcpServers. Mitigation: upgrade to 1.0.74 or later.
Original description
The description as published by the source.
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 unconditionally enabled all project MCP servers via enableAllProjectMcpServers, an attacker who opened a pull request containing a malicious .mcp.json file could achieve arbitrary code execution on the GitHub Actions runner and exfiltrate secrets available to the workflow (such as API keys and tokens) when a privileged user or an automatic trigger invoked the Claude action on the pull request. This issue is fixed in version 1.0.74, which restores .claude/ and .mcp.json from the pull request base branch before the CLI runs.
Source: GitHub Security Advisories (Global) NVD GitHub Advisory
Auto-generated summary
Assembled by SecPulse from the source data (CVSS, CWE, affected versions) using templates — no AI involved. Check the original description and references below for exact details.
A vulnerability tracked as CVE-2026-47751 has been found in anthropics/claude-code-action.
Attackers can target a specific entry point like enableAllProjectMcpServers over the network to misuse the product.
Risk of unauthorized operations or information disclosure.
What to do: upgrade anthropics/claude-code-action to 1.0.74 or later.
If unsure, ask your IT team or search "anthropics/claude-code-action CVE-2026-47751" on the vendor's site.
CVE-2026-47751 (anthropics/claude-code-action) — CWE-78
Attack surface: enableAllProjectMcpServers
Patched: 1.0.74 — apply immediately
Plan: 1) Audit SBOM/dependencies, 2) Stage→prod upgrade, 3) Add WAF/proxy monitoring on affected endpoints, 4) Hunt IOCs in logs.
Refs: see the GHSA / vendor advisory / patched release linked on this page.
OS command injection (CWE-78) exists in anthropics/claude-code-action. Attackers reach the vulnerable code path via enableAllProjectMcpServers.
Check the vendor advisory for the affected versions of anthropics/claude-code-action. Attack surface: enableAllProjectMcpServers.
Severity: ?. Risk of unauthorized operations or information disclosure.
Update to 1.0.74.
Until the patch is applied: disable the affected feature, apply WAF rules, or restrict access via network ACLs.
Search webserver/proxy logs for unusual request patterns matching this CVE's known IOCs. Run grep -r 'anthropics/claude-code-action' . against your dependency files (package-lock.json, requirements.txt, go.sum) to find affected services.
Response actions
Concrete steps and command examples for SOC/SRE teams to execute in order
-
1Identify exposure identify
grep -r 'anthropics/claude-code-action' . | grep -v node_modulesリポジトリと本番環境の依存ファイル (package-lock.json / requirements.txt / go.sum / Gemfile.lock 等) で
anthropics/claude-code-actionを grep し、稼働しているサービス・バージョンを把握する。 -
2Apply patch patch
Upgrade anthropics/claude-code-action to 1.0.74ステージング環境で 1.0.74 に上げて回帰テスト → 本番反映。回帰テストはアプリの主要ハッピーパスを含めること。
-
3Post-deployment verification verify
Confirm patched version is live in productionパッチ適用後、ステージングで PoC または同等の悪用パターンを再現して脆弱性が閉じたことを確認。本番ではアクセスログ・WAF でアラート再発が無いか継続監視。
Affected packages
References
- advisory github.com
- advisory nvd.nist.gov
- advisory github.com
- package github.com
- patch github.com
- patch github.com
- web github.com
- web github.com