registry / @saiteja1123/mcp-server / 1.1.9

@saiteja1123/mcp-server@1.1.9

Vibesecur MCP security scanner — universal account config, multi-project CRU, folder locking, cross-IDE

AI Security Review

scanned 4h ago · by lpm-firewall-ai

Review flagged AI-agent configuration or capability changes. This remains warn-only unless evidence shows foreign-agent hijack through preinstall/install/postinstall, hidden persistence, exfiltration, remote code execution, or other concrete malicious behavior.

Static reason

One or more suspicious static signals were detected.

Trigger

User runs vibesecur-mcp init with --write, then an IDE starts the configured MCP server or invokes a scan.

Impact

A user-authorized global MCP registration can expose selected scan input to the configured backend.

Mechanism

explicit agent-config registration and remote source-code scanning

Rationale

No install-time execution or covert malicious chain was found. The remaining risk is an explicit broad AI-agent setup capability coupled with remote scanning.

Evidence

package.jsonsrc/cli.jssrc/mcp-config.mjssrc/api-scan.mjssrc/lock.mjs~/.cursor/mcp.json~/.codeium/windsurf/mcp_config.json%APPDATA%/Claude/claude_desktop_config.json.vscode/mcp.json.vibesecur/lock.json

Network endpoints5

vibesecur.onrender.com/api/v1/mcp/bind/api/v1/mcp/verify-install

@saiteja1123/mcp-server@1.1.9

AI Security Review

Decision evidence

Source & flagged code

Source & flagged code

Findings

Source & flagged code