Trust Assessment
melo-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 Excessive Permissions via Generic Remote Workbench Tool.
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 | Excessive Permissions via Generic Remote Workbench Tool The skill exposes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The generic nature of `run_composio_tool()` suggests it might allow execution of arbitrary Composio tools or code, potentially granting the LLM overly broad capabilities beyond specific 'Melo operations'. If `run_composio_tool()` is not strictly sandboxed or limited to a predefined set of safe operations, a compromised LLM could use this to perform unauthorized actions, data exfiltration, or command injection through the underlying Composio platform. The lack of specific constraints or examples for `run_composio_tool()` raises a significant security concern. Clarify and restrict the capabilities of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure it operates within a strictly defined and minimal scope necessary for 'Melo operations'. If it allows arbitrary code execution or access to sensitive system functions, consider removing it or implementing strong guardrails and explicit user confirmation for such powerful operations. Provide specific examples or detailed documentation of what `run_composio_tool()` can and cannot do, and how its execution is secured. | LLM | SKILL.md:68 |
Scan History
Embed Code
[](https://skillshield.io/report/cb8c2b9d62bf8b6e)
Powered by SkillShield