Is @biggora/claude-plugins safe to install?

@biggora/claude-plugins was flagged as CRITICAL RISK (risk score 1251) with 113 findings detected across 189 files. Review the findings before installing.

What security issues were found in @biggora/claude-plugins?

Sigil detected 113 findings in @biggora/claude-plugins, including patterns related to obfuscation, install_hooks, credentials, network_exfil, code_patterns. See the full scan report for details.

Scans/npm/@biggora/claude-plugins

@biggora/claude-plugins

npm

Summary

@biggora/claude-plugins v1.2.0 was classified as CRITICAL RISK with a risk score of 1251. Sigil detected 113 findings across 189 files, covering phases including obfuscation, install hooks, credential access, network exfiltration, code patterns. Review the findings below before installing this package.

CRITICAL RISK(1251)

v1.2.0

28 March 2026, 10:30 UTC

by Sigil Bot

Risk Score

1251

Findings

113

Files Scanned

189

Provenance

Registry

https://www.npmjs.com/package/@biggora/claude-plugins/v/1.2.0

Scanned From

https://registry.npmjs.org/@biggora/claude-plugins/-/claude-plugins-1.2.0.tgz

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

package/gemini-cli-workspace/iteration-2/eval-viewer.html:649

    // ---- Embedded data (injected by generate_review.py) ----
    const EMBEDDED_DATA = {"skill_name": "gemini-cli", "runs": [{"id": "eval-1-cicd-setup-with_skill", "prompt": "I want to set up gemini cli in my CI/CD pipeline on GitHub Actions so it can automatically review PRs. We use an API key stored in GitHub secrets. How do I set this up with structured JSON output so I can parse the review?", "eval_id": 1, "outputs": [{"name": "response.md", "type": "text", "content": "# Setting Up Gemini

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/npm/@biggora/claude-plugins)](https://sigilsec.ai/scans/B089884F-928F-47E4-9854-DD4EBECFE9BB)

HTML

<a href="https://sigilsec.ai/scans/B089884F-928F-47E4-9854-DD4EBECFE9BB"><img src="https://sigilsec.ai/badge/npm/@biggora/claude-plugins" alt="Sigil Scan"></a>

Run This Scan Yourself