Skip to main content
Scans/github/claude-world/claude-agent

claude-world/claude-agent

github

Share

Summary

claude-world/claude-agent v2026-03-22 was classified as CRITICAL RISK with a risk score of 272. Sigil detected 18 findings across 111 files, covering phases including network exfiltration, provenance, install hooks, code patterns. Review the findings below before installing this package.

Package description: Persistent personal assistant powered by Claude Code — autonomous memory, 13 skills, 4 MCP servers, content pipeline, OpenClaw migration

CRITICAL RISK(272)

v2026-03-22

23 March 2026, 00:01 UTC

by Sigil Bot

Risk Score

272

Findings

18

Files Scanned

111

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-makefile-curl

HIGH

Makefile/script pipes remote content to shell

repo/README.md:380

```bash
curl -LsSf https://astral.sh/uv/install.sh | sh
```
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.

install-makefile-curl

HIGH

Makefile/script pipes remote content to shell

repo/README.md:583

- **Node.js** >= 18 — For hooks (uses only built-in `fs` and `path` modules)
- **uv** (optional) — For MCP servers. Install: `curl -LsSf https://astral.sh/uv/install.sh | sh`
- No additional npm dependencies
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.

install-makefile-curl

HIGH

Makefile/script pipes remote content to shell

repo/app/client/components/McpPage.tsx:249

              <p>notebooklm: {t('mcp.nlmSetup') || 'Run `uvx notebooklm login` once (opens browser for Google login).'}</p>
              <p>{t('mcp.uvxNote') || 'All servers require `uvx`. Install: curl -LsSf https://astral.sh/uv/install.sh | sh'}</p>
            </div>
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.

install-makefile-curl

HIGH

Makefile/script pipes remote content to shell

repo/app/client/i18n.ts:75

    'mcp.nlmSetup': 'Run `uvx notebooklm login` once (opens browser for Google login).',
    'mcp.uvxNote': 'All servers require `uvx`. Install: curl -LsSf https://astral.sh/uv/install.sh | sh',
    'settings.save': 'Save Settings',
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.

install-makefile-curl

HIGH

Makefile/script pipes remote content to shell

repo/app/client/i18n.ts:304

    'mcp.nlmSetup': '執行 `uvx notebooklm login` 一次(開啟瀏覽器進行 Google 登入)。',
    'mcp.uvxNote': '所有伺服器需要 `uvx`。安裝:curl -LsSf https://astral.sh/uv/install.sh | sh',
    'settings.saving': '儲存中...',
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.

install-makefile-curl

HIGH

Makefile/script pipes remote content to shell

repo/app/client/i18n.ts:530

    'mcp.nlmSetup': '`uvx notebooklm login`を一度実行(ブラウザでGoogleログイン)。',
    'mcp.uvxNote': '全サーバーに`uvx`が必要。インストール:curl -LsSf https://astral.sh/uv/install.sh | sh',
    'settings.saving': '保存中...',
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

Sigil scan badge for github/claude-world/claude-agent

Markdown

[![Sigil Scan](https://sigilsec.ai/badge/github/claude-world/claude-agent)](https://sigilsec.ai/scans/9A084905-F5D7-4869-B9BC-98C600154072)

HTML

<a href="https://sigilsec.ai/scans/9A084905-F5D7-4869-B9BC-98C600154072"><img src="https://sigilsec.ai/badge/github/claude-world/claude-agent" alt="Sigil Scan"></a>

Run This Scan Yourself

Scan your own packages

Run Sigil locally to audit any package before it touches your codebase.

curl -sSL https://sigilsec.ai/install.sh | sh
Read the docs →Free. Apache 2.0.

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.

Scanned bySigil Bot