Security Audit
waboxapp-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
waboxapp-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 Generic tool 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 | |
|---|---|---|---|---|
| HIGH | Generic tool execution via RUBE_REMOTE_WORKBENCH The skill exposes `RUBE_REMOTE_WORKBENCH` which is described as enabling `run_composio_tool()` for 'Bulk ops'. Given the skill's stated purpose is 'Waboxapp Automation', the generic naming `run_composio_tool()` strongly suggests the ability to execute any Composio tool, not just those related to Waboxapp. This constitutes excessive permissions, as it could allow the LLM to perform actions outside the intended scope of Waboxapp operations, potentially leading to unintended data access or system manipulation if other Composio tools are available and more privileged. Restrict the capabilities of `RUBE_REMOTE_WORKBENCH` to only execute tools within the 'waboxapp' toolkit, or explicitly clarify in the skill description that its scope is limited to Waboxapp operations. If `run_composio_tool()` is inherently generic, consider if this skill truly requires access to such a broad tool, or if a more narrowly scoped alternative should be used. | LLM | SKILL.md:72 |
Scan History
Embed Code
[](https://skillshield.io/report/59e9b01f05ab7988)
Powered by SkillShield