Security Audit

genderapi-io-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

genderapi-io-automation received a trust score of 85/100, 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 Tool Execution via Rube 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 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

85%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad Tool Execution via Rube MCP The skill documentation describes the use of `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which are part of the Rube MCP. These tools allow the LLM to discover and execute arbitrary tools available through the Rube platform, not just those specifically related to Genderapi IO. This grants overly broad tool access, potentially allowing the LLM to interact with other systems or data beyond the intended scope of 'Genderapi IO automation' if not properly constrained by the host environment. The skill's reliance on a general-purpose tool execution platform (Rube MCP) without explicit scope limitation in the skill's definition itself poses a risk of excessive permissions. Implement strict access controls and sandboxing for the LLM's interaction with Rube MCP. Ensure that the LLM can only discover and execute tools explicitly whitelisted for its current task, or that the Rube MCP itself enforces fine-grained permissions based on the calling context. The host LLM should validate `tool_slug` against an allowed list before invoking `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH`.	LLM	SKILL.md:49

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/acf1f91e50cd6686.svg)](https://skillshield.io/report/acf1f91e50cd6686)