Security Audit

rafflys-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 6 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

rafflys-automation received a trust score of 93/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.

SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Broad Tool Execution via Multi-Capability Provider (MCP).

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

93%

Dependency Graph

100%

LLM Behavioral Safety

100%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Broad Tool Execution via Multi-Capability Provider (MCP) The skill acts as an interface to the 'rube' Multi-Capability Provider (MCP), which allows for dynamic discovery and execution of various tools via `RUBE_SEARCH_TOOLS` and `RUBE_MULTI_EXECUTE_TOOL`. This design grants the LLM using this skill the ability to execute a wide range of operations exposed by the 'rafflys' toolkit through the 'rube' MCP. While this is the intended functionality, it represents a significant permission scope. If the 'rube' MCP exposes sensitive or destructive operations, or if the LLM is not properly constrained, it could lead to unintended actions or data manipulation within the Rafflys system. Ensure that the 'rube' MCP and the underlying 'rafflys' toolkit enforce strict authorization and scope control for all exposed tools. Implement robust access control mechanisms within the MCP to limit the actions an LLM can perform. Additionally, LLM developers should employ careful prompt engineering and internal policy enforcement to restrict the LLM's use of `RUBE_MULTI_EXECUTE_TOOL` to only necessary and authorized operations.	Static	SKILL.md:48

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/4cc10c5fe08d852d.svg)](https://skillshield.io/report/4cc10c5fe08d852d)