Security Audit
files-com-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
files-com-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 Potential for broad execution 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 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 | Potential for broad execution via RUBE_REMOTE_WORKBENCH The skill documentation advertises `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' using `run_composio_tool()`. While the exact capabilities and sandboxing of `run_composio_tool()` are not detailed in this documentation, the term 'Remote Workbench' and 'Bulk ops' suggests a powerful execution environment. This could allow an AI agent to perform broader operations or potentially execute arbitrary code if the underlying tool is not strictly sandboxed and validated, leading to excessive permissions. Clarify the exact scope and sandboxing of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure it cannot execute arbitrary code or shell commands. If it's intended for complex scripting, ensure strict input validation and a secure, least-privilege execution environment. | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/b93d47a124471065)
Powered by SkillShield