Security Audit

strava-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

strava-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 Skill promotes use of tools with broad execution 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

85%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill promotes use of tools with broad execution capabilities The skill documentation guides the LLM to use Rube MCP tools such as `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. `RUBE_MULTI_EXECUTE_TOOL` allows executing any tool slug discovered via `RUBE_SEARCH_TOOLS`. More critically, the 'Quick Reference' section mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops', implying the ability to execute any Composio tool, not just those related to Strava. These capabilities grant very broad permissions to external services or potentially local system interactions if the underlying Composio tools allow it. This exposes the LLM to a wide attack surface if it can be prompted to use these powerful tools for unintended purposes, going beyond the stated 'Strava Automation' scope. Restrict the scope of tools exposed to the LLM via Rube MCP to only Strava-specific operations. Implement strict input validation and sanitization for arguments passed to `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to prevent arbitrary tool execution. Ensure the underlying Composio tools operate with the principle of least privilege. Add explicit warnings in the documentation about the broad capabilities of these tools and the potential security implications.	LLM	SKILL.md:70

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/fb96252cc557adb0.svg)](https://skillshield.io/report/fb96252cc557adb0)