Security Audit
short-menu-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
short-menu-automation received a trust score of 86/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Dynamic Tool Execution with Broad Scope.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Dynamic Tool Execution with Broad Scope The skill instructs the agent LLM to dynamically discover and execute tools provided by the Rube MCP. Specifically, it guides the LLM to use `RUBE_SEARCH_TOOLS` to find available tools and then `RUBE_MULTI_EXECUTE_TOOL` to execute them based on dynamically retrieved `tool_slug` and `arguments`. Additionally, `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` is mentioned for 'Bulk ops', suggesting a powerful, potentially unconstrained execution environment. This pattern grants the agent LLM broad and dynamic execution capabilities. If the underlying Rube MCP exposes tools with sensitive permissions (e.g., filesystem access, arbitrary network requests, system commands), a malicious user could potentially trick the LLM into discovering and executing harmful operations by crafting specific prompts. The skill itself does not define the scope or safety of these Rube tools, but by instructing their dynamic use, it enables a potentially excessive permission model. Implement strict sandboxing and access controls for tools exposed by the Rube MCP. Ensure that `RUBE_SEARCH_TOOLS` only returns tools appropriate for the agent's context and that `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` calls are subject to robust permission checks and input validation. Consider limiting the scope of dynamically discoverable tools or requiring explicit user confirmation for sensitive operations, especially when dealing with tools that have broad system access. | LLM | SKILL.md:39 |
Scan History
Embed Code
[](https://skillshield.io/report/d8ca1f9dc508fd0f)
Powered by SkillShield