Runner code execution via untrusted MCP configuration
Published Jul 16, 2026 · Updated Jul 16, 2026
Command injection in Anthropic Claude Code Action before 1.0.74 allows remote authenticated users to execute code on GitHub Actions runners. The action checks out a pull request's head, reads its .mcp.json through default setting sources, and enables every project MCP server before permission gating. A repository must use the action on pull requests, and a privileged user or automatic trigger must invoke it; successful execution can expose workflow secrets.
Summary
What happened
Command injection in Anthropic Claude Code Action before 1.0.74 allows remote authenticated users to execute code on GitHub Actions runners. The action checks out a pull request's head, reads its .mcp.json through default setting sources, and enables every project MCP server before permission gating. A repository must use the action on pull requests, and a privileged user or automatic trigger must invoke it; successful execution can expose workflow secrets.
The record
- CVE
- CVE-2026-47751
- Published
- Jul 16, 2026
- Updated
- Jul 16, 2026
- Vendor
- Anthropic
- Product
- Claude Code Action
- Classifications
- CWE-78, CWE-200, T1059
- Attack vector
- network
- Privileges
- authenticated
Timeline
How it unfolded
- Jul 16, 2026CVE publishedPublication date reported by the CVE source.
- Jul 16, 2026Record updatedLatest update available in the CVE record.
Exploitability
Present is not the same as exploitable
Compare your product and version with the public record. A matching version still requires validation against your environment.
Is a vulnerable build present?
Compare these published version ranges with your installed build and any vendor patches.
- Affected versionversion=< 1.0.74
What conditions does exploitation require?
What is affected?
Published CVSS scores
CVSS describes severity. EPSS estimates exploitation probability.
Attacks
What attackers are doing with it
Daily unique IPs observed by Shadowserver honeypots for known exploited vulnerabilities (KEVs). Missing observations do not establish an absence of attacks.
Weakness, pattern, technique
Public exploit references
No public exploit references are available in this record.
Labels summarize the accepted research assessment. They do not indicate a test against your environment.
Technologies
Your stack
See the directory against your own environment.
Your stack
Check the software in your environment
Book a demo to see how Hinoki identifies affected software and validates exploitability in your environment.
Book a demo