Code execution via untrusted MCP server commands
Published Jul 17, 2026 · Updated Jul 17, 2026
Command execution in Tailcall ForgeCode 2.11.1 allows attackers to run code when a local user starts it in an untrusted repository. At startup, the project-local .mcp.json loader passes each mcpServers command and args directly to a child process without a trust prompt. Execution requires a local user to start ForgeCode inside an attacker-controlled repository, after which the command runs with that user's privileges and can read, alter, or destroy accessible data.
Summary
What happened
Command execution in Tailcall ForgeCode 2.11.1 allows attackers to run code when a local user starts it in an untrusted repository. At startup, the project-local .mcp.json loader passes each mcpServers command and args directly to a child process without a trust prompt. Execution requires a local user to start ForgeCode inside an attacker-controlled repository, after which the command runs with that user's privileges and can read, alter, or destroy accessible data.
The record
- CVE
- CVE-2026-57860
- Published
- Jul 17, 2026
- Updated
- Jul 17, 2026
- Vendor
- Tailcall, Inc.
- Product
- ForgeCode
- Classifications
- CWE-829, T1204.002
- Attack vector
- local
- Privileges
- unauthenticated
Timeline
How it unfolded
- Jul 17, 2026CVE publishedPublication date reported by the CVE source.
- Jul 17, 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=2.11.1
What conditions does exploitation require?
What is affected?
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
- ForgeCode untrusted-repository proof of conceptfunctional · demonstrated
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