Summary
stefanogebara/restaurant-ai-mcp v2026-03-22 was classified as CRITICAL RISK with a risk score of 3846. Sigil detected 385 findings across 921 files, covering phases including provenance, network exfiltration, install hooks, code patterns, obfuscation. Review the findings below before installing this package.
Package description: AI Restaurant Phone Receptionist MCP Server - Handles reservations via ElevenLabs voice agent
v2026-03-22
22 March 2026, 23:35 UTC
by Sigil Bot
Risk Score
3846
Findings
385
Files Scanned
921
Provenance
Findings by Phase
Phase Ordering
Phases are ordered by criticality, with the most dangerous at the top. Click any phase header to expand or collapse its findings. Critical phases are expanded by default.
install-pip-setup-exec
CRITICALsetup.py executes code at install time
repo/client/public/js/convai-widget-embed.js:36
`).filter(a=>a.trim()!=="a=extmap-allow-mixed").join(`
`);e.RTCSessionDescription&&r instanceof e.RTCSessionDescription?arguments[0]=new e.RTCSessionDescription({type:r.type,sdp:s}):r.sdp=s}return n.apply(this,arguments)}}function Nc(e,t){if(!(e.RTCPeerConnection&&e.RTCPeerConnection.prototype))return;const n=e.RTCPeerConnection.prototype.addIceCandidate;!n||n.length===0||(e.RTCPeerConnection.prototype.addIceCandidate=function(){return arguments[0]?(t.browser==="chrome"&&t.version<78||t.browser=Why was this flagged?
This setup.py calls subprocess, os.system, exec, or eval during package installation. Legitimate packages rarely need to execute arbitrary commands at install time. This pattern is commonly used by malicious packages to download and run payloads, exfiltrate environment variables, or establish persistence. Rated CRITICAL because it runs with the installer's full permissions.
Badge
Markdown
[](https://sigilsec.ai/scans/8D8559C3-C1BE-49B9-864E-12A690B5D20A)HTML
<a href="https://sigilsec.ai/scans/8D8559C3-C1BE-49B9-864E-12A690B5D20A"><img src="https://sigilsec.ai/badge/github/stefanogebara/restaurant-ai-mcp" alt="Sigil Scan"></a>Run This Scan Yourself
Scan your own packages
Run Sigil locally to audit any package before it touches your codebase.
Early Access
Get cloud scanning, threat intel, and CI/CD integration.
Join 150+ developers on the waitlist.
Get threat intelligence and product updates
Security research, new threat signatures, and product updates. No spam.
Other github scans
Believe this result is incorrect? Request a review or see our Terms of Service and Methodology.