Security Audit
composio-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
composio-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/Data Exfiltration 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/Data Exfiltration via RUBE_REMOTE_WORKBENCH The skill mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The name 'Remote Workbench' strongly suggests a powerful execution environment that could potentially allow arbitrary code execution, shell commands, or access to sensitive files/environment variables if `run_composio_tool()` is not properly sandboxed or restricted. While the skill does not explicitly demonstrate an exploit, the existence of such a tool without clear limitations or warnings represents a significant attack surface for command injection or data exfiltration. Clarify the exact capabilities and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure these tools are properly sandboxed and restrict access to sensitive system resources. Provide explicit warnings if they can execute arbitrary code or access files, and detail any necessary input validation or security controls. | LLM | SKILL.md:64 |
Scan History
Embed Code
[](https://skillshield.io/report/b342a1d4fffa9177)
Powered by SkillShield