Security Audit

agentql-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

agentql-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 capabilities 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

Network Access

1 finding

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad tool execution capabilities via Rube MCP The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH`. `RUBE_MULTI_EXECUTE_TOOL` allows for the execution of any discovered `agentql` tool. More critically, `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` suggests the ability to execute arbitrary Composio tools. If the underlying `agentql` or Composio tools have access to sensitive operations (e.g., filesystem, network, external APIs, or arbitrary code execution), an attacker could craft a prompt to the LLM to misuse these capabilities, leading to data exfiltration, unauthorized actions, or even command injection. The skill itself does not impose restrictions on the types of tools that can be executed, making it a powerful, and potentially risky, interface. Implement stricter access controls or allow-lists for the `agentql` and Composio tools that can be executed via Rube MCP. Ensure that `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` are heavily sandboxed and only allow execution of pre-approved, safe operations. The skill description should also explicitly warn about the power of these tools and recommend careful use.	LLM	SKILL.md:60

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/6b28310587939ab9.svg)](https://skillshield.io/report/6b28310587939ab9)