Trust Assessment
setup-automatik 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 5 findings: 3 critical, 2 high, 0 medium, and 0 low severity. Key findings include Arbitrary command execution, Remote code execution: curl/wget pipe to shell, Direct Request for SSH Credentials.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 40/100, 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 Findings5
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Arbitrary command execution Remote code download piped to interpreter 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/alltomatos/aetup-automatik/SKILL.md:38 | |
| CRITICAL | Remote code execution: curl/wget pipe to shell Detected a pattern that downloads and immediately executes remote code. This is a primary malware delivery vector. Never pipe curl/wget output directly to a shell interpreter. | Static | skills/alltomatos/aetup-automatik/SKILL.md:38 | |
| CRITICAL | Direct Request for SSH Credentials The skill explicitly instructs the user to provide highly sensitive SSH credentials (Public IP Address, Username, SSH Password, or Private Key) directly into the chat. This poses a critical risk of credential harvesting and data exfiltration, as these credentials could be stored, logged, misused, or exfiltrated by a compromised or malicious agent. Providing private keys or passwords directly to an LLM-based agent is an insecure practice and creates a prompt injection vector if the input is crafted maliciously. Avoid asking for raw SSH credentials directly in the chat. Implement secure out-of-band mechanisms for credential provision (e.g., secure vault integration, temporary tokens, or agent-managed SSH keys with restricted access). If direct access is absolutely necessary, ensure robust input validation and sanitization, and clearly communicate the risks to the user. | LLM | SKILL.md:38 | |
| HIGH | Agent Executes Commands with Elevated Privileges on VPS The skill's core functionality involves executing shell commands and scripts (`assets/SetupOrion.sh`) directly on a remote VPS, often with root privileges (as implied by 'Username (usually `root`)'). This creates a significant command injection vulnerability if user-provided input (e.g., domain names, database credentials, tool names, or pairing codes) is not rigorously sanitized before being incorporated into the commands or script arguments. The `curl -fsSL https://get.openclaw.ai | sh` pattern for OpenClaw Node Pairing also introduces a supply chain risk and potential for arbitrary code execution with elevated privileges. Implement strict input validation and sanitization for all user-provided data used in shell commands or script arguments. Use parameterized commands or dedicated APIs instead of string concatenation for command construction. Review `SetupOrion.sh` thoroughly for injection vulnerabilities. Avoid `curl | sh` for installation; prefer package managers or verified installation scripts with integrity checks. | LLM | SKILL.md:30 | |
| HIGH | Critical Installation Script Unscanned The skill relies heavily on `assets/SetupOrion.sh`, a large external shell script that is central to its installation functionality. This script was skipped during the automated scan due to its size (1.2MB), meaning its contents are unknown and unaudited. This poses a significant supply chain risk, as malicious or vulnerable code within this script could lead to arbitrary code execution, data exfiltration, or system compromise on the user's VPS. Thoroughly review and audit the `SetupOrion.sh` script for security vulnerabilities, malicious code, and adherence to best practices. Consider breaking down large scripts into smaller, auditable modules. Pin the version of the script or use cryptographic hashes to ensure its integrity before execution. | LLM | SKILL.md:87 |
Scan History
Embed Code
[](https://skillshield.io/report/aa6182a6e9c33cfb)
Powered by SkillShield