Security Audit

dovetail-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

dovetail-automation received a trust score of 84/100, 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 Execution Capability via RUBE_REMOTE_WORKBENCH, Unversioned External MCP Dependency.

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

Manifest Analysis

100%

Static Code Analysis

100%

Dependency Graph

100%

LLM Behavioral Safety

78%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad Execution Capability via RUBE_REMOTE_WORKBENCH The skill documentation suggests using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This implies a powerful execution capability that, if not properly sandboxed or constrained, could allow for arbitrary code execution, command injection, or unauthorized access to resources on the remote workbench. The vague description of this tool's functionality raises concerns about its potential for misuse. Clarify the exact capabilities and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that execution within the remote workbench is strictly sandboxed, limited to predefined safe operations, and cannot be used to execute arbitrary system commands or access unauthorized resources. Provide examples of what `run_composio_tool()` can and cannot do.	LLM	SKILL.md:69
MEDIUM	Unversioned External MCP Dependency The skill explicitly depends on the 'Rube MCP' as indicated by `"requires": {"mcp": ["rube"]}` in the manifest and the instruction to connect to `https://rube.app/mcp`. No specific version for the 'rube' MCP is declared. This lack of version pinning means that updates to the Rube MCP could introduce breaking changes or security vulnerabilities without explicit review, posing a supply chain risk. The security of this skill is directly tied to the trustworthiness and ongoing security of the `rube.app` platform. If possible within the ecosystem's manifest capabilities, specify a minimum or exact version for the 'rube' MCP dependency to ensure stability and security. Provide guidance on how users can verify the integrity and security of external MCPs before integrating them.	LLM	Manifest:4

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/83d869273ee8b639.svg)](https://skillshield.io/report/83d869273ee8b639)