Security Audit
ip2proxy-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
ip2proxy-automation received a trust score of 85/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Generic Tool Execution via Rube MCP.
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 Findings1
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| MEDIUM | Generic Tool Execution via Rube MCP The skill utilizes `RUBE_MULTI_EXECUTE_TOOL` and references `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`. These are generic mechanisms for executing tools provided by the Rube MCP system. While the skill's stated context is 'Ip2proxy Automation', the skill description itself does not explicitly restrict the `tool_slug` or `run_composio_tool()` calls to only Ip2proxy-specific operations. If the Rube MCP system provides tools with broad permissions (e.g., filesystem access, arbitrary command execution, or network requests outside the intended scope), a malicious prompt could potentially manipulate the LLM to discover and execute such tools. This could lead to data exfiltration, command injection, or other unauthorized actions. The skill's recommendation to 'Always search first' for tools further emphasizes the dynamic nature of tool selection, increasing the risk if the available toolset is not strictly controlled. Implement strict allow-listing or scope enforcement for `tool_slug` arguments within the skill's execution context, ensuring only Ip2proxy-related tools can be invoked. If `RUBE_REMOTE_WORKBENCH` allows arbitrary tool execution, ensure it operates within a highly restricted sandbox and that `run_composio_tool()` is limited to a safe subset of functions. The Rube MCP system itself should enforce least privilege for its tools. | LLM | SKILL.md:46 |
Scan History
Embed Code
[](https://skillshield.io/report/e977cf1651989b6d)
Powered by SkillShield