Is dbrown725/mcp-human-resources-client safe to install?

dbrown725/mcp-human-resources-client was flagged as CRITICAL RISK (risk score 95) with 11 findings detected across 22 files. Review the findings before installing.

What security issues were found in dbrown725/mcp-human-resources-client?

Sigil detected 11 findings in dbrown725/mcp-human-resources-client, including patterns related to provenance, install_hooks, network_exfil, code_patterns. See the full scan report for details.

Scans/github/dbrown725/mcp-human-resources-client

dbrown725/mcp-human-resources-client

github

Summary

dbrown725/mcp-human-resources-client v2026-03-18 was classified as CRITICAL RISK with a risk score of 95. Sigil detected 11 findings across 22 files, covering phases including provenance, install hooks, network exfiltration, code patterns. Review the findings below before installing this package.

Package description: An AI-powered agent hub with a Python Eel web UI, built on Pydantic AI and the Model Context Protocol (MCP). Connects to multiple MCP servers. The user can orchestrate employee management through n...

CRITICAL RISK(95)

v2026-03-18

20 March 2026, 11:49 UTC

by Sigil Bot

Risk Score

Findings

Files Scanned

Provenance

Registry

https://github.com/dbrown725/mcp-human-resources-client

Repository

https://github.com/dbrown725/mcp-human-resources-client

Scanned From

https://github.com/dbrown725/mcp-human-resources-client.git

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-makefile-curl

HIGH

Makefile/script pipes remote content to shell

repo/README.md:132

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
You may need to close your terminal and open a new one afterwards.

Why was this flagged?

A script or Makefile pipes content from a remote URL directly into a shell (curl | sh or wget | bash). This is inherently dangerous because the remote content can change at any time, and the command runs with the current user's permissions. Rated HIGH because it requires manual execution (unlike install hooks) but still executes arbitrary remote code.

Badge

Markdown

[![Sigil Scan](https://sigilsec.ai/badge/github/dbrown725/mcp-human-resources-client)](https://sigilsec.ai/scans/32051E0C-5CE7-4F19-90B0-8EA75036D9E0)

HTML

<a href="https://sigilsec.ai/scans/32051E0C-5CE7-4F19-90B0-8EA75036D9E0"><img src="https://sigilsec.ai/badge/github/dbrown725/mcp-human-resources-client" alt="Sigil Scan"></a>

Run This Scan Yourself