Security Audit

habitica-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

habitica-automation received a trust score of 95/100, 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 Skill exposes general-purpose Rube MCP tools with broad capabilities.

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

93%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Skill exposes general-purpose Rube MCP tools with broad capabilities The `habitica-automation` skill instructs the LLM to use Rube MCP tools such as `RUBE_SEARCH_TOOLS`, `RUBE_MANAGE_CONNECTIONS`, `RUBE_MULTI_EXECUTE_TOOL`, and `RUBE_REMOTE_WORKBENCH`. While the skill's stated purpose is 'Habitica automation', these Rube MCP tools are general-purpose and may allow the LLM to interact with or manage connections for any toolkit supported by Rube MCP, not just Habitica. For example, `RUBE_MANAGE_CONNECTIONS` can manage connections for any `toolkit`, and `RUBE_MULTI_EXECUTE_TOOL` can execute any tool discovered via `RUBE_SEARCH_TOOLS`. The `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` is particularly broad, potentially allowing execution of any Composio tool. This broad access, even if guided by the skill's prompt towards Habitica, could be exploited if the LLM is prompted to perform actions outside the intended scope, leading to unintended access or actions on other connected services. 1. Restrict Rube MCP scope: Configure the Rube MCP instance used by this skill to only expose Habitica-specific tools and connections, or to filter `RUBE_SEARCH_TOOLS` results to only Habitica tools. 2. LLM Guardrails: Implement strong LLM guardrails to ensure that tool calls are strictly confined to the Habitica domain, even when using general-purpose Rube MCP tools. 3. Tool-specific permissions: If possible, define more granular permissions for the `rube` MCP dependency in the skill manifest to limit access to only Habitica-related functionalities.	LLM	SKILL.md:35

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/f023aa5c06541d02.svg)](https://skillshield.io/report/f023aa5c06541d02)