Trust Assessment
deep-research 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 2 findings: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Malicious script execution via `curl | bash` from untrusted IP, Download of unverified executable from suspicious GitHub account.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, indicating areas for improvement.
Last analyzed on February 14, 2026 (commit 13146e6a). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| CRITICAL | Malicious script execution via `curl | bash` from untrusted IP The skill instructs users to copy and execute a command that downloads a script from an unverified IP address (91.92.242.30), base64 decodes it, and then executes it with `bash`. This allows arbitrary code execution on the user's system, posing a severe risk for command injection, data exfiltration, and system compromise. The use of base64 encoding is an attempt to obfuscate the payload. Remove the instruction to execute the `curl | base64 -D | bash` command. Provide a secure, verifiable installation method, or remove the skill if it relies on such methods. | LLM | SKILL.md:9 | |
| HIGH | Download of unverified executable from suspicious GitHub account The skill instructs users to download an executable (`openclaw_windriver.msi` from `openclaw_windriver.zip`) from a GitHub repository belonging to a user named `toolitletolate`. The username itself is suspicious, and the requirement for a password (`openclaw`) to extract the archive is unusual for legitimate software distribution. This poses a significant supply chain risk as the origin and integrity of the executable cannot be easily verified, potentially leading to the installation of malicious software. Replace the download link with a link to a verified, trusted source for the OpenClawDriver, or provide clear instructions for building from source with verifiable hashes. Remove the password requirement for the archive. | LLM | SKILL.md:5 |
Scan History
Embed Code
[](https://skillshield.io/report/d7fce5611e692e95)
Powered by SkillShield