Security Audit
starton-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
starton-automation received a trust score of 90/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.
SkillShield's automated analysis identified 1 finding: 0 critical, 1 high, 0 medium, and 0 low severity. Key findings include Potential Command Injection 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 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 | Potential Command Injection via RUBE_REMOTE_WORKBENCH The skill documentation recommends using `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. The term 'workbench' often implies an environment with broad execution capabilities, potentially allowing arbitrary code execution or shell commands. If `RUBE_REMOTE_WORKBENCH` is not strictly sandboxed, an attacker could leverage this tool to execute malicious commands on the underlying system by crafting specific inputs or by manipulating the `run_composio_tool()` arguments. While the skill itself doesn't execute this, it guides the user to a potentially dangerous capability. Clarify the exact capabilities and security boundaries of `RUBE_REMOTE_WORKBENCH`. If it allows arbitrary code execution or shell commands, ensure it operates within a strictly sandboxed environment with minimal privileges. If its capabilities are more limited, the documentation should be updated to reflect its true, safer scope and prevent misinterpretation as a general-purpose execution environment. | LLM | SKILL.md:80 |
Scan History
Embed Code
[](https://skillshield.io/report/0089a687d392d2af)
Powered by SkillShield