Trust Assessment
coding-agent received a trust score of 65/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 3 findings: 1 critical, 1 high, 1 medium, and 0 low severity. Key findings include MacOS OpenClawDriver Installation via Obfuscated Command Injection, Windows OpenClawDriver Installation from Suspicious Source, Global Package Installation via npm.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 48/100, 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 Findings3
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | MacOS OpenClawDriver Installation via Obfuscated Command Injection The skill explicitly instructs users to execute a base64-decoded command that downloads and runs a script from an unencrypted IP address (http://91.92.242.30). This is a severe command injection and supply chain risk, allowing arbitrary code execution from an untrusted source without integrity checks. Remove the base64-encoded command. If an external driver is required, provide a secure, verified installation method, preferably from a trusted package manager or signed executable, using HTTPS and cryptographic hashes for integrity verification. | LLM | SKILL.md:15 | |
| HIGH | Windows OpenClawDriver Installation from Suspicious Source The skill instructs users to download and run an MSI installer from a GitHub repository under a suspicious username ('toolitletolate'). The provided password ('openclaw') for the zip archive is weak and could be a social engineering tactic. Running executables from unverified sources is a significant supply chain risk and can lead to arbitrary code execution. Provide a secure, verified installation method for the Windows driver. This should involve a trusted source, signed executables, and clear instructions for verifying the integrity of the download (e.g., checksums). Avoid using weak passwords for archives. | LLM | SKILL.md:12 | |
| MEDIUM | Global Package Installation via npm The skill explicitly instructs the installation of a global npm package (`@mariozechner/pi-coding-agent`). Global package installations can introduce supply chain risks if the package or its dependencies are malicious or compromised, potentially affecting other projects or the system environment. Avoid instructing global package installations. If a package is necessary, recommend local installation within a project or a sandboxed environment (e.g., virtual environment, container). Provide guidance on verifying package integrity. | LLM | SKILL.md:99 |
Scan History
Embed Code
[](https://skillshield.io/report/a57696669ba7f555)
Powered by SkillShield