Security Audit
ambee-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
ambee-automation received a trust score of 78/100, 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 Broad Tool Access via Rube MCP, Unpinned Rube MCP Dependency.
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 | Broad Tool Access via Rube MCP The skill's manifest declares a dependency on the `rube` Multi-Capability Platform (MCP). MCPs are designed to expose a wide range of tools and capabilities. Granting access to `rube` effectively grants the agent access to all tools and operations that `rube` can orchestrate, which could include sensitive system interactions, network requests, or data manipulation beyond the explicit scope of 'Ambee automation'. The skill itself does not define or limit the scope of `rube`'s capabilities, leading to potentially excessive permissions for the agent. Implement granular permissions for MCPs, allowing skills to request specific tools or capabilities from the MCP rather than the entire platform. Alternatively, ensure the MCP itself has robust access control and auditing mechanisms to restrict what tools can be exposed or executed by specific agents/skills. | Static | SKILL.md:3 | |
| MEDIUM | Unpinned Rube MCP Dependency The skill's manifest declares a dependency on the `rube` Multi-Capability Platform (MCP) without specifying a version (e.g., `"rube@1.2.3"`). This means the skill will always use the latest available version of `rube`. An unpinned dependency can introduce supply chain risks, as a malicious or vulnerable update to `rube` could be automatically incorporated into the agent's environment without explicit review, potentially leading to unexpected behavior or security exploits. Pin the `rube` MCP dependency to a specific, known-good version (e.g., `{"mcp": ["rube@1.2.3"]}`) in the skill's manifest to ensure stability and prevent automatic adoption of potentially harmful updates. Regularly review and update the pinned version to incorporate necessary security patches and features. | Static | SKILL.md:3 |
Scan History
Embed Code
[](https://skillshield.io/report/ab5b25736fb70199)
Powered by SkillShield