ForgeCode (tailcallhq/forgecode), an AI pair-programming CLI, automatically loads and executes the MCP servers defined in a repository's .mcp.json file on startup without user confirmation. A malicious repository can supply a crafted .mcp.json whose mcpServers entries specify arbitrary command and args values (for example, command: bash with args: ['-c', 'touch /tmp/pwned']). When a user runs the forge CLI inside a cloned untrusted repository, the specified commands are spawned with the invoking user's privileges, resulting in arbitrary code execution. This provides a reliable initial-access and persistence primitive against developers who evaluate untrusted repositories with ForgeCode.
Fix
Nothing published yet: no patch, vendor advisory or mitigation reference on NVD, no vendor advisory in the News for this CVE, not in CISA's KEV, no fixed package version. BaselineWatch does not guess at one.
Change history 1
- First seenCVSS 8.4NVD modified 2026-10-24 20:10
Affected (CPE criteria) 0
NVD has not attached CPE configurations yet.
References 6
- https://github.com/tailcallhq/forgecode
- https://github.com/tailcallhq/forgecode/commit/68ca3a3a26c73c38a700453d3d021b5bbdc15dbd
- https://github.com/tailcallhq/forgecode/issues/3022
- https://github.com/tailcallhq/forgecode/issues/3252
- https://www.vulncheck.com/advisories/forgecode-arbitrary-code-execution-via-unvetted-mcp-json-in-untrusted-repository
- https://github.com/tailcallhq/forgecode/issues/3022