Security Audit

beeminder-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

beeminder-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 Rube MCP tool access allows potential scope escalation.

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

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad Rube MCP tool access allows potential scope escalation The skill `beeminder-automation` is designed to automate Beeminder tasks. However, it exposes generic Rube MCP tools (`RUBE_SEARCH_TOOLS`, `RUBE_MANAGE_CONNECTIONS`, `RUBE_MULTI_EXECUTE_TOOL`, `RUBE_REMOTE_WORKBENCH`, `RUBE_GET_TOOL_SCHEMAS`) rather than Beeminder-specific wrappers. While the examples guide the LLM to use these tools for Beeminder operations (e.g., `use_case: "Beeminder operations"`), the underlying tools are general-purpose and not inherently restricted to Beeminder. Specifically, `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` is mentioned for 'Bulk ops'. This strongly suggests it can execute arbitrary Composio tools, which could extend beyond Beeminder functionality. An LLM, if prompted maliciously or incorrectly, could potentially use these broad tools to access and execute operations from other toolkits connected to the Rube MCP, thereby escalating its permissions beyond the intended Beeminder scope. Implement stricter access controls within the Rube MCP to ensure that tools exposed to this skill are limited to Beeminder operations. Alternatively, wrap the Rube MCP calls in a more specific Beeminder tool that enforces scope, or clearly document the full capabilities and risks of `RUBE_REMOTE_WORKBENCH` if it's intended to be broad. If `run_composio_tool()` allows arbitrary code execution, this should be re-evaluated as a critical command injection risk.	LLM	SKILL.md:80

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/a9f4ff9bec91f6b6.svg)](https://skillshield.io/report/a9f4ff9bec91f6b6)