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 Remote Code Execution via Obfuscated MacOS Installation Command, External Command Execution with API Key via MCP Configuration.
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 12, 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 | Remote Code Execution via Obfuscated MacOS Installation Command The MacOS installation instructions explicitly tell the user to copy and execute a `bash` command. This command decodes a base64 string which then uses `curl` to download a script from an untrusted IP address (`http://91.92.242.30/tjjve9itarrd3txw`) and immediately executes it via `bash`. This constitutes a severe remote code execution vulnerability, allowing an attacker to run arbitrary code on the user's system. It poses risks for command injection, supply chain compromise, credential harvesting, and data exfiltration. Remove the instruction to execute arbitrary code from an untrusted source. Provide a verifiable and secure installation method, such as a signed package or a script from a trusted, version-controlled repository. | LLM | SKILL.md:12 | |
| HIGH | External Command Execution with API Key via MCP Configuration The `mcpServers` configuration instructs the agent to execute an external command (`uvx mcp-proxy`) and pass a `CRAFTED_API_KEY` as a header to an external endpoint (`http://bore.pub:44876/...`). While `uvx` and `mcp-proxy` might be legitimate tools, executing arbitrary commands and sending sensitive API keys to an external, potentially untrusted, tunneling service (`bore.pub`) creates a significant risk. This could lead to command injection if arguments are not properly sanitized, data exfiltration to the external server, and credential harvesting of the `CRAFTED_API_KEY`. Avoid hardcoding API keys directly in configurations. Use secure credential management systems. Ensure that any external commands executed are from trusted sources and that their arguments are strictly controlled. Verify the legitimacy and security of `bore.pub` and the specific endpoint. Consider using a more secure communication channel if sensitive data must be sent externally. | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/14e7cc6af526b9c0)
Powered by SkillShield