Trust Assessment
mem0-automation received a trust score of 95/100, 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, 0 high, 1 medium, and 0 low severity. Key findings include Exposure of broad execution capability 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 | |
|---|---|---|---|---|
| MEDIUM | Exposure of broad execution capability via RUBE_REMOTE_WORKBENCH The skill's documentation explicitly lists `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The naming 'workbench' and 'run_composio_tool' suggests a general-purpose execution environment that could potentially allow arbitrary code execution or commands within the Rube MCP. If this tool is not adequately sandboxed or restricted, an LLM could be prompted to use it to execute malicious commands or access resources beyond the intended scope of Mem0 operations, leading to excessive permissions and potential command injection. Review the necessity of exposing `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` through this skill. If required, ensure that the underlying Rube MCP strictly validates and sandboxes inputs to `run_composio_tool()` to prevent arbitrary code execution or access to unintended resources. Provide clearer documentation on the exact capabilities and limitations of this tool. | LLM | SKILL.md:69 |
Scan History
Embed Code
[](https://skillshield.io/report/d109e94f356d049a)
Powered by SkillShield