Trust Assessment
lightning received a trust score of 10/100, placing it in the Untrusted category. This skill has significant security findings that require attention before use in production.
SkillShield's automated analysis identified 13 findings: 11 critical, 1 high, 0 medium, and 1 low severity. Key findings include Network egress to untrusted endpoints, Arbitrary command execution, Node lockfile missing.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The Manifest Analysis layer scored lowest at 0/100, indicating areas for improvement.
Last analyzed on February 13, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings13
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Network egress to untrusted endpoints HTTP request to raw IP address Review all outbound network calls. Remove connections to webhook collectors, paste sites, and raw IP addresses. Legitimate API calls should use well-known service domains. | Manifest | skills/clawd21/lightning/scripts/lightning.js:651 | |
| CRITICAL | Arbitrary command execution Node.js child_process require Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/clawd21/lightning/scripts/download-binary.js:9 | |
| CRITICAL | Arbitrary command execution Node.js child_process require Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/clawd21/lightning/scripts/lightning.js:9 | |
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/clawd21/lightning/scripts/lightning.js:16 | |
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/clawd21/lightning/scripts/lightning.js:23 | |
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/clawd21/lightning/scripts/lightning.js:32 | |
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/clawd21/lightning/scripts/lightning.js:38 | |
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/clawd21/lightning/scripts/lightning.js:289 | |
| CRITICAL | Arbitrary command execution Node.js synchronous shell execution Review all shell execution calls. Ensure commands are static (not built from user input), use absolute paths, and are strictly necessary. Prefer library APIs over shell commands. | Manifest | skills/clawd21/lightning/scripts/lightning.js:311 | |
| CRITICAL | LLM instructed to exfiltrate API key from user's email The skill explicitly instructs the host LLM to use an 'email skill' to search for and extract a Breez API key from the user's email inbox. This is a direct prompt injection attempt to manipulate the LLM into performing data exfiltration of sensitive credentials, which could lead to unauthorized access to the user's financial services. Remove the instruction for the LLM to use an email skill to extract sensitive information. The user should be instructed to manually provide the API key, or a secure, explicit API should be used for credential handling. | LLM | SKILL.md:170 | |
| CRITICAL | Command injection via execSync with unvalidated user input The `printQRCode` function in `scripts/lightning.js` uses `child_process.execSync` to execute shell commands (`qrencode` and `python3 -c ...`). The `data` and `outputFile` variables are directly interpolated into these commands without proper sanitization or escaping. If `data` or `outputFile` contain malicious shell metacharacters (e.g., `;`, `|`, `&`, `$()`), an attacker could execute arbitrary commands on the host system. Replace `execSync` with safer alternatives like `child_process.spawn` or `child_process.execFile` with arguments passed as an array, or ensure all user-controlled input is rigorously sanitized and escaped before being used in shell commands. For Python, consider using a Python library directly within Node.js (e.g., `python-shell`) or ensure the Python script itself handles input securely. | LLM | scripts/lightning.js:16 | |
| HIGH | Unverified binary downloaded via postinstall script The `package.json` defines a `postinstall` script that executes `scripts/download-binary.js`. This script downloads a prebuilt native binary (`lni_js.node`) from a GitHub release URL (`https://github.com/lightning-node-interface/lni/releases`). There is no checksum verification (e.g., SHA256) of the downloaded binary. This introduces a significant supply chain risk: if the GitHub repository or release assets are compromised, a malicious binary could be downloaded and executed automatically upon `npm install`, leading to arbitrary code execution on the host system. Implement cryptographic verification (e.g., SHA256 checksum) for the downloaded binary. The expected checksum should be hardcoded or securely fetched and compared against the downloaded file's checksum before execution. Alternatively, consider building the binary from source during installation if feasible, or using a trusted package manager for native modules. | LLM | package.json:7 | |
| LOW | Node lockfile missing package.json is present but no lockfile was found (package-lock.json, pnpm-lock.yaml, or yarn.lock). Commit a lockfile for deterministic dependency resolution. | Dependencies | skills/clawd21/lightning/package.json |
Scan History
Embed Code
[](https://skillshield.io/report/610ed6758043f8f0)
Powered by SkillShield