Security Audit

api-sports-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

CAUTION

Scanned 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

api-sports-automation received a trust score of 74/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Excessive Permissions via Broad Tool Access, Supply Chain Risk from Unverified External MCP Endpoint.

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

70%

Behavioral Risk Signals

Network Access

2 findings

Shell Execution

2 findings

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Excessive Permissions via Broad Tool Access The skill grants the LLM access to powerful tools like `RUBE_MULTI_EXECUTE_TOOL` for 'API Sports operations' and `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' using `run_composio_tool()`. The `run_composio_tool()` function, in particular, suggests the ability to execute a wide range of Composio tools, potentially beyond the scope of API Sports, depending on the underlying Rube MCP configuration. This broad access, without explicit restrictions or fine-grained permissions defined within the skill, could allow a compromised or maliciously prompted LLM to perform destructive actions, access sensitive data, or execute unintended operations on external services. Implement stricter access controls or scope limitations for the tools exposed. If `RUBE_REMOTE_WORKBENCH` can execute arbitrary Composio tools, consider if this level of access is truly necessary for the skill's stated purpose. Provide guidance on how to configure the Rube MCP to limit the scope of tools available to this skill, if possible. Ensure that any operations performed by the LLM are subject to user confirmation for sensitive actions.	LLM	SKILL.md:70
HIGH	Supply Chain Risk from Unverified External MCP Endpoint The skill relies entirely on an external Managed Control Plane (MCP) server located at `https://rube.app/mcp` for its core functionality, as indicated in the manifest's `requires` field and the setup instructions. There is no mechanism specified (e.g., version pinning, cryptographic hashes, or trusted registry) to verify the integrity or authenticity of the tools and schemas served by this external endpoint. A compromise of `rube.app` could lead to malicious tools being served to the LLM, potentially allowing arbitrary code execution, data exfiltration, or unauthorized actions on behalf of the user. Implement mechanisms to verify the integrity and authenticity of external MCP endpoints and the tools they provide. This could include using a trusted registry, cryptographic signing of tool definitions, or version pinning with checksums. Provide clear instructions for users on how to validate the MCP server's authenticity before connecting.	LLM	SKILL.md:20

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/f64e9da4378eeb10.svg)](https://skillshield.io/report/f64e9da4378eeb10)