Trust Assessment
y-gy-automation 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 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Unversioned External MCP Dependency, Potentially Excessive Permissions via RUBE_REMOTE_WORKBENCH.
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 17, 2026 (commit 99e2a295). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Unversioned External MCP Dependency The skill explicitly depends on an external Managed Control Plane (MCP) hosted at `https://rube.app/mcp`. This dependency is unversioned and unpinned, meaning the behavior, capabilities, or security posture of the MCP could change at any time without the skill's knowledge or explicit update. A compromised or malicious MCP could direct the agent to perform unauthorized actions, leading to significant supply chain risks for any system integrating this skill. To mitigate supply chain risks, specify a trusted, versioned endpoint for the Rube MCP. Implement mechanisms to verify the integrity and expected behavior of the MCP before use, such as cryptographic signatures or content hashes. Consider using a trusted, audited provider or hosting critical MCP components internally. | Static | SKILL.md:10 | |
| HIGH | Potentially Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill instructs the agent to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`. The term 'workbench' and the function name 'run_composio_tool' strongly suggest the capability to execute arbitrary code, scripts, or highly privileged operations within the Composio environment. If this tool is not properly sandboxed, restricted, or if its inputs are not rigorously validated, it could allow an attacker to achieve command injection, data exfiltration, or other unauthorized actions by manipulating the agent's input to this tool. Implement strict access controls and robust sandboxing for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Clearly define and limit the scope of operations that can be performed through this tool. Ensure comprehensive input validation to prevent command injection or arbitrary code execution. Provide explicit warnings about the power of this tool in its documentation and ensure agents are only granted access to it when absolutely necessary and under strict supervision. | Static | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/26390cdf4904cd3e)
Powered by SkillShield