Trust Assessment
moz-automation received a trust score of 83/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Unpinned MCP dependency, Potential arbitrary code execution 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 20, 2026 (commit 27904475). 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 | Potential arbitrary code execution via RUBE_REMOTE_WORKBENCH The `RUBE_REMOTE_WORKBENCH` tool, specifically when used with `run_composio_tool()`, is vaguely described as handling 'Bulk ops'. The documentation does not specify the nature of `run_composio_tool()`'s arguments or execution environment. If `run_composio_tool()` allows arbitrary code or script execution, it presents a significant command injection vulnerability, enabling an attacker to execute malicious commands on the underlying system or within the agent's environment. This also implies excessive permissions if the workbench can perform operations beyond the intended scope of Moz tasks. Clarify the exact capabilities and input sanitization of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. If it allows arbitrary code, restrict its functionality or remove it. If it is intended for specific, safe operations, document the allowed inputs and ensure strict validation and sandboxing. | LLM | SKILL.md:80 | |
| MEDIUM | Unpinned MCP dependency The skill's manifest specifies a dependency on the 'rube' MCP without a specific version. This can lead to supply chain risks if a future version of 'rube' introduces vulnerabilities or malicious behavior, as the skill would automatically use the latest available version. It is best practice to pin dependencies to a known, secure version. Specify a precise version for the 'rube' MCP dependency in the `requires` section of the manifest (e.g., `{"mcp": ["rube@1.2.3"]}`) to ensure consistent and secure behavior. | LLM | SKILL.md |
Scan History
Embed Code
[](https://skillshield.io/report/fe8d3555681d25e9)
Powered by SkillShield