Security Audit

dovetail-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

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 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 Broad access to Dovetail operations via Rube MCP, Dependency on external Rube MCP service.

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

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

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad access to Dovetail operations via Rube MCP The skill exposes tools (`RUBE_MULTI_EXECUTE_TOOL`, `RUBE_REMOTE_WORKBENCH`) that allow the LLM to execute arbitrary Dovetail operations through the Rube MCP. The scope of these operations is limited only by the permissions granted to the Rube MCP connection to Dovetail, not by the skill itself. This could lead to the LLM performing sensitive actions (e.g., data modification, deletion, access to private information) if the underlying connection has broad permissions. The `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` is particularly broad, enabling execution of any Composio tool. Implement more granular access control within the Rube MCP for Dovetail connections, or introduce explicit user confirmation steps for sensitive operations executed via the LLM. Consider defining a more restricted set of allowed Dovetail operations for the skill.	LLM	SKILL.md:49
MEDIUM	Dependency on external Rube MCP service The skill explicitly depends on an external Multi-Cloud Platform (MCP) server hosted at `https://rube.app/mcp`. The security and integrity of this skill are directly tied to the trustworthiness and security posture of the `rube.app` service. A compromise of this external service could lead to unauthorized access or manipulation of Dovetail data. While not a traditional package dependency, this represents a critical external dependency in the skill's operational chain. Users should thoroughly vet the `rube.app` service and its security practices. Skill developers should consider providing options for self-hosting or using alternative, vetted MCPs if available, or clearly state the trust assumptions.	LLM	SKILL.md:21

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/89d22108f3fd6bec.svg)](https://skillshield.io/report/89d22108f3fd6bec)