Security Audit
everhour-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
everhour-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 Broad 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 | Broad tool execution via RUBE_REMOTE_WORKBENCH The skill is named 'everhour-automation' and its manifest describes it as automating 'Everhour tasks'. However, it exposes `RUBE_REMOTE_WORKBENCH` which uses `run_composio_tool()`. The term 'Composio tool' is generic and implies the ability to execute any tool available through the Composio platform, not just those specific to Everhour. If `RUBE_REMOTE_WORKBENCH` allows execution of tools from other Composio toolkits (e.g., GitHub, Jira, etc.) that might be connected via Rube MCP, this skill would grant permissions far beyond its stated purpose, leading to excessive permissions and potential privilege escalation to other connected services. Restrict the `RUBE_REMOTE_WORKBENCH` functionality to only execute tools from the `everhour` toolkit. Alternatively, if broader access is intended, the skill's name and description should be updated to accurately reflect its wider capabilities and the associated permissions. | LLM | SKILL.md:79 |
Scan History
Embed Code
[](https://skillshield.io/report/8a89ddc8f33c2f75)
Powered by SkillShield