Security Audit
everhour-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
everhour-automation received a trust score of 81/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.
SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Broad Access to Everhour API via Rube MCP, Potential Command Injection 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 17, 2026 (commit 99e2a295). SkillShield performs automated 4-layer security analysis on AI skills and MCP servers.
Layer Breakdown
Behavioral Risk Signals
Security Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Potential Command Injection via `RUBE_REMOTE_WORKBENCH` The `RUBE_REMOTE_WORKBENCH` tool, specifically mentioning the ability to execute `run_composio_tool()`, provides a programmatic interface that could potentially be exploited for command injection. If the arguments passed to `run_composio_tool()` are not rigorously validated and sanitized by the Rube MCP platform, or if the underlying Composio tools allow arbitrary code execution, an attacker could craft malicious inputs to execute unintended commands within the Composio environment. This could lead to data manipulation, unauthorized access, or system compromise. Ensure that the Rube MCP platform strictly validates and sanitizes all arguments passed to `run_composio_tool()` to prevent arbitrary command execution. The underlying Composio tools should also be designed to prevent command injection. Agents should be instructed to only pass well-defined and safe arguments according to the tool's schema. | LLM | SKILL.md:59 | |
| MEDIUM | Broad Access to Everhour API via Rube MCP The skill grants the agent broad programmatic access to Everhour operations through `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. This allows the agent to perform any action permitted by the connected Everhour account, including potentially sensitive operations like managing projects, tasks, and time entries. While this is the intended functionality of an automation skill, it represents a significant permission level that requires careful management and monitoring to prevent misuse or unauthorized actions. Implement strict access controls and monitoring for the agent and the Everhour account connected to Rube MCP. Ensure the agent operates with the principle of least privilege, only having access to the specific Everhour functionalities required for its tasks. Regularly review agent activity logs. | LLM | SKILL.md:59 |
Scan History
Embed Code
[](https://skillshield.io/report/148fa2c341624be1)
Powered by SkillShield