CVE-2026-57860: Inclusion of Functionality from Untrusted Control Sphere in tailcallhq forgecode
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.
AI Analysis
Technical Summary
CVE-2026-57860 affects ForgeCode version 2.11.1, an AI pair-programming CLI tool. The vulnerability arises because ForgeCode automatically loads and executes MCP servers defined in a repository's .mcp.json file on startup without user confirmation. An attacker can supply a malicious .mcp.json file with mcpServers entries specifying arbitrary commands and arguments (e.g., command: bash, args: ['-c', 'touch /tmp/pwned']). When a user runs the forge CLI inside such a repository, these commands execute with the user's privileges, resulting in arbitrary code execution. This behavior provides a reliable initial access and persistence mechanism against developers who run ForgeCode in untrusted repositories.
Potential Impact
Successful exploitation allows arbitrary code execution with the privileges of the user running ForgeCode. This can lead to initial access, persistence, and potentially further compromise of the developer's environment. The vulnerability is triggered by simply running the forge CLI inside a malicious repository, making it a significant risk for developers who evaluate untrusted code.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, users should avoid running ForgeCode inside untrusted repositories or disable automatic loading/execution of MCP servers if possible. Monitor vendor communications for updates and apply patches promptly once released.
CVE-2026-57860: Inclusion of Functionality from Untrusted Control Sphere in tailcallhq forgecode
Description
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.
CVSS v4.0
Score 8.4high
Affected software
pkg:github/tailcallhq/forgecodeRun on your own infrastructure? Check whether these packages are installed with threat-finder — our free open-source scanner.
AI-Powered Analysis
Machine-generated threat intelligence
Technical Analysis
CVE-2026-57860 affects ForgeCode version 2.11.1, an AI pair-programming CLI tool. The vulnerability arises because ForgeCode automatically loads and executes MCP servers defined in a repository's .mcp.json file on startup without user confirmation. An attacker can supply a malicious .mcp.json file with mcpServers entries specifying arbitrary commands and arguments (e.g., command: bash, args: ['-c', 'touch /tmp/pwned']). When a user runs the forge CLI inside such a repository, these commands execute with the user's privileges, resulting in arbitrary code execution. This behavior provides a reliable initial access and persistence mechanism against developers who run ForgeCode in untrusted repositories.
Potential Impact
Successful exploitation allows arbitrary code execution with the privileges of the user running ForgeCode. This can lead to initial access, persistence, and potentially further compromise of the developer's environment. The vulnerability is triggered by simply running the forge CLI inside a malicious repository, making it a significant risk for developers who evaluate untrusted code.
Mitigation Recommendations
Patch status is not yet confirmed — check the vendor advisory for current remediation guidance. Until an official fix is available, users should avoid running ForgeCode inside untrusted repositories or disable automatic loading/execution of MCP servers if possible. Monitor vendor communications for updates and apply patches promptly once released.
Technical Details
- Data Version
- 5.2
- Assigner Short Name
- VulnCheck
- Date Reserved
- 2026-06-25T18:48:00.283Z
- Cvss Version
- 4.0
- State
- PUBLISHED
- Remediation Level
- null
Threat ID: 6a5b5eba2d1edb114c7fb778
Added to database: 07/18/2026, 11:08:42 UTC
Last enriched: 07/25/2026, 22:47:46 UTC
Last updated: 08/31/2026, 10:52:10 UTC
Views: 82
Community Reviews
0 reviewsCrowdsource mitigation strategies, share intel context, and vote on the most helpful responses. Sign in to add your voice and help keep defenders ahead.
Want to contribute mitigation steps or threat intel context? Sign in or create an account to join the community discussion.
Actions
Updates to AI analysis require Pro Console access. Upgrade inside Console → Billing.
Need more coverage?
Upgrade to Pro Console for AI refresh and higher limits.
For incident response and remediation, OffSeq services can help resolve threats faster.
Latest Threats
Check if your credentials are on the dark web
Instant breach scanning across billions of leaked records. Free tier available.