Security Audit
demio-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
demio-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 Broad Tool Access 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 | Broad Tool Access via RUBE_REMOTE_WORKBENCH The skill documentation describes `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' using `run_composio_tool()`. This suggests a powerful, general-purpose execution capability that, if not properly constrained by the underlying Rube MCP implementation or the LLM's safety mechanisms, could lead to the LLM performing a wide range of actions on Demio without granular control or explicit user confirmation. The documentation itself does not specify any limitations or safety measures for this broad access, potentially leading to excessive permissions if the LLM misinterprets its scope. Add explicit warnings or guidance in the documentation regarding the scope and potential impact of `RUBE_REMOTE_WORKBENCH`. Recommend that the underlying Rube MCP or Composio toolkit implement stricter access controls, require explicit user confirmation for sensitive bulk operations, or provide more granular tools instead of a general 'workbench' for bulk operations. | LLM | SKILL.md:70 |
Scan History
Embed Code
[](https://skillshield.io/report/23fede370e5d5862)
Powered by SkillShield