Security Audit
docupost-automation
github.com/ComposioHQ/awesome-claude-skillsTrust Assessment
docupost-automation received a trust score of 82/100, 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 Excessive Permissions via Remote Workbench, Broad Tool Execution Capability.
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 Findings2
| Severity | Finding | Layer | Location | |
|---|---|---|---|---|
| HIGH | Excessive Permissions via Remote Workbench The skill exposes `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` capability. A 'remote workbench' implies a highly privileged execution environment, and `run_composio_tool()` suggests the ability to execute arbitrary functions or scripts within the Composio ecosystem. This broad access could allow the LLM to perform actions beyond its intended scope, potentially leading to data exfiltration, unauthorized modifications, or even command injection if the underlying `run_composio_tool()` is not strictly sandboxed and validated. Clarify the exact capabilities and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that the Rube MCP strictly sandboxes this environment, validates all inputs, and restricts the types of operations that can be performed. Consider implementing explicit human approval for sensitive operations invoked via this tool or restricting the LLM's access to it. | LLM | SKILL.md:80 | |
| MEDIUM | Broad Tool Execution Capability The skill grants the LLM access to `RUBE_MULTI_EXECUTE_TOOL`, allowing it to execute any tool discovered for the `docupost` toolkit. While this is core to the skill's functionality, it means the LLM has broad, unconstrained access to all Docupost operations exposed by the toolkit. If any of these underlying Docupost tools have vulnerabilities, unintended side effects, or can be misused, the LLM could trigger them, leading to unauthorized actions or data manipulation. Ensure that all tools within the `docupost` toolkit are thoroughly audited for security vulnerabilities and adhere to the principle of least privilege. Implement fine-grained access controls within the Rube MCP to restrict the LLM's ability to call specific Docupost tools or operations if its role is limited. Provide clear documentation on the security implications of each tool. | LLM | SKILL.md:57 |
Scan History
Embed Code
[](https://skillshield.io/report/a4f2dccb83082c08)
Powered by SkillShield