Security Audit

bubble-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

bubble-automation received a trust score of 88/100, 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 access to Rube MCP via `requires`.

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

85%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad access to Rube MCP via `requires` The skill's manifest declares a requirement for broad access to the entire `rube` MCP (`"mcp": ["rube"]`). The `SKILL.md` describes Rube MCP as a system capable of orchestrating 'Bubble operations' and executing 'Composio tools' via `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. Without specific constraints on the `rube` tools available or their capabilities, this grants the skill (and by extension, a potentially malicious prompt) broad access to execute arbitrary operations exposed by Rube. If Rube's underlying tools are not sufficiently sandboxed or restricted, this could lead to sensitive system interactions, data manipulation, or exfiltration. The skill explicitly encourages dynamic tool discovery, meaning any tool exposed by Rube could be used if prompted. Restrict the `requires` clause in the manifest to specific, known-safe Rube tools or capabilities if possible, rather than granting access to the entire `rube` MCP. Ensure that the Rube MCP itself enforces strict access controls, sandboxing, and input validation for the tools it exposes, especially for powerful execution tools like `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`.	LLM	Manifest

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/e987eff68bbaef79.svg)](https://skillshield.io/report/e987eff68bbaef79)