Trust Assessment
lmnt-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, 1 high, 0 medium, and 0 low severity. Key findings include Skill exposes broad RUBE_REMOTE_WORKBENCH for arbitrary tool execution.
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 | |
|---|---|---|---|---|
| HIGH | Skill exposes broad RUBE_REMOTE_WORKBENCH for arbitrary tool execution The skill's `SKILL.md` explicitly lists `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` as an approach for 'Bulk ops'. This encourages the LLM to use a highly privileged tool that can execute arbitrary Composio tools. If the underlying Composio tools have broad access (e.g., to file systems, network, or other sensitive APIs), this could lead to excessive permissions being granted to the LLM, allowing it to perform actions beyond the intended scope of 'Lmnt automation' or to access sensitive resources. The skill does not provide any specific constraints or warnings about the scope of `run_composio_tool()`. Restrict the scope of `RUBE_REMOTE_WORKBENCH` or `run_composio_tool()` calls within the skill definition to specific, limited operations. Provide clear warnings and guidelines on its use, emphasizing that it should only be used for explicitly authorized and scoped tasks. If `run_composio_tool()` can execute *any* Composio tool, consider if this level of generality is truly necessary for 'Lmnt automation' or if more specific, constrained tools should be exposed instead. | LLM | SKILL.md:74 |
Scan History
Embed Code
[](https://skillshield.io/report/69607fad97e4b1d7)
Powered by SkillShield