Security Audit
supadata-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
supadata-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 Exposure of potentially broad RUBE_REMOTE_WORKBENCH tool.
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 | Exposure of potentially broad RUBE_REMOTE_WORKBENCH tool The skill explicitly exposes `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' which can execute `run_composio_tool()`. Without clear documentation or constraints on the capabilities of `run_composio_tool()`, this tool could grant the LLM excessive permissions, potentially allowing arbitrary code execution or broad data manipulation within the Supadata environment or other connected systems via Composio. The skill encourages its use without detailing its security implications. Provide clear documentation for `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`, detailing their exact capabilities, potential side effects, and any security implications. Implement strict access controls and input validation for these tools. Consider if such a broad tool is necessary for the skill's intended purpose or if more granular tools should be exposed instead to limit the LLM's operational scope. | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/fe5e1fcca347d102)
Powered by SkillShield