GHSA-8q5r-mmjf-575q
Suggest an improvement- Source
- https://github.com/advisories/GHSA-8q5r-mmjf-575q
- Import Source
- https://github.com/github/advisory-database/blob/main/advisories/github-reviewed/2026/06/GHSA-8q5r-mmjf-575q/GHSA-8q5r-mmjf-575q.json
- JSON Data
- https://api.osv.dev/v1/vulns/GHSA-8q5r-mmjf-575q
- Aliases
- Published
- 2026-06-10T19:33:48Z
- Modified
- 2026-06-10T19:45:08.200152510Z
- Severity
-
- 5.3 (Medium) CVSS_V4 - CVSS:4.0/AV:N/AC:L/AT:P/PR:L/UI:N/VC:L/VI:L/VA:N/SC:H/SI:H/SA:N CVSS Calculator
- Summary
- Claude Code Action: Malicious MCP Server Configuration in PRs Enables Remote Code Execution and Secret Exfiltration
- Details
-
Due to the combination of checking out PR head branches (attacker-controlled), reading
.mcp.jsonfrom the working directory via default setting sources, and unconditionally enabling all project MCP servers viaenableAllProjectMcpServers, it was possible for an attacker who opened a PR containing a malicious.mcp.jsonfile 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.
- Database specific
{ "cwe_ids": [ "CWE-200", "CWE-78" ], "severity": "MODERATE", "github_reviewed_at": "2026-06-10T19:33:48Z", "github_reviewed": true, "nvd_published_at": null }- References