Security Audit
basin-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
basin-automation received a trust score of 65/100, 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: 1 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection via RUBE_REMOTE_WORKBENCH, Potential Prompt Injection via RUBE_SEARCH_TOOLS `use_case` parameter.
The analysis covered 4 layers: Manifest Analysis, Static Code Analysis, Dependency Graph, LLM Behavioral Safety. The LLM Behavioral Safety layer scored lowest at 55/100, indicating areas for improvement.
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 | |
|---|---|---|---|---|
| CRITICAL | Potential Command Injection via RUBE_REMOTE_WORKBENCH The skill documentation mentions `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. The term 'workbench' and the function `run_composio_tool()` strongly suggest an environment capable of executing arbitrary code or commands. Without strict sandboxing and robust input validation, this could allow an attacker to inject and execute malicious commands on the host system or within the Rube MCP environment, leading to full system compromise, data exfiltration, or denial of service. The `RUBE_REMOTE_WORKBENCH` tool should be thoroughly reviewed for its security implications. If it allows arbitrary code execution, it must be run in a strictly sandboxed environment with minimal permissions. Implement robust input validation and sanitization for all arguments passed to `run_composio_tool()` to prevent command injection. Clearly document the security model and limitations of this tool. | LLM | SKILL.md:80 | |
| HIGH | Potential Prompt Injection via RUBE_SEARCH_TOOLS `use_case` parameter The `RUBE_SEARCH_TOOLS` function takes a `use_case` parameter, described as 'your specific Basin task'. If this parameter is directly used in an underlying LLM prompt or search query without proper sanitization or escaping, a malicious user could inject instructions to manipulate the LLM's behavior, extract sensitive information, or bypass security controls. Implement strict input validation and sanitization for the `use_case` parameter of `RUBE_SEARCH_TOOLS`. Ensure that any user-provided input for this parameter is properly escaped or filtered before being incorporated into an LLM prompt or search query to prevent prompt injection attacks. Consider using a separate, constrained input field for user intent rather than a free-form text field if the backend uses an LLM. | LLM | SKILL.md:39 |
Scan History
Embed Code
[](https://skillshield.io/report/834fabb665936115)
Powered by SkillShield