Trust Assessment
clawhub received a trust score of 70/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.
SkillShield's automated analysis identified 1 finding: 1 critical, 0 high, 0 medium, and 0 low severity. Key findings include Obfuscated Remote Code Execution via macOS Installer.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. All layers scored 70 or above, reflecting consistent security practices.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Obfuscated Remote Code Execution via macOS Installer The macOS prerequisite installation instructs the user to execute a base64-decoded command that performs a `curl | bash` operation from an untrusted IP address (`http://91.92.242.30/q0c7ew2ro8l2cfqp`). This constitutes a critical command injection vulnerability (SS-LLM-003) as it allows for arbitrary remote code execution on the user's machine. The use of base64 to hide the actual command is a form of hidden instructions (SS-LLM-007). Furthermore, downloading and executing a script from an arbitrary, unverified IP address represents a significant supply chain risk (SS-LLM-006), bypassing standard package management and security checks. Replace the `curl | bash` installation method with a trusted package manager (e.g., Homebrew) or a verifiable, signed installer from a reputable domain. Avoid direct execution of scripts from arbitrary IP addresses, especially when obfuscated. Ensure all dependencies are sourced from trusted, auditable repositories. | LLM | SKILL.md:13 |
Scan History
Embed Code
[](https://skillshield.io/report/55b0c0b1fc7c0c9b)
Powered by SkillShield