Security Audit

gleap-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

gleap-automation received a trust score of 73/100, 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 Tool Execution Permissions via Rube MCP, Broad Remote Workbench Access.

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

70%

Behavioral Risk Signals

Shell Execution

2 findings

Dynamic Code

1 finding

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Excessive Tool Execution Permissions via Rube MCP The skill instructs the LLM to use `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` which grant overly broad execution capabilities. `RUBE_MULTI_EXECUTE_TOOL` allows the LLM to dynamically discover and execute any Gleap operation available through Rube MCP. `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` further extends this to any Composio tool. This means an LLM, if compromised or misused, could perform arbitrary actions within the Gleap system or other Composio-integrated systems, potentially leading to data manipulation, unauthorized access, or service disruption. The skill does not define or enforce any granular restrictions on which specific Gleap or Composio operations can be performed. Restrict the scope of operations the LLM can perform. Instead of a generic `RUBE_MULTI_EXECUTE_TOOL`, consider exposing specific, pre-approved Gleap operations as distinct tools. For `RUBE_REMOTE_WORKBENCH`, ensure that the `run_composio_tool()` function is only used for explicitly whitelisted and safe operations, or remove its usage if not strictly necessary. Implement granular access controls at the Rube MCP or Composio platform level to limit the actions an LLM can take, even if it requests a broad operation.	LLM	SKILL.md:49
HIGH	Broad Remote Workbench Access The skill explicitly mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This tool provides a mechanism for executing arbitrary Composio tools, which can encompass a wide range of functionalities across various integrated services. Granting an LLM the ability to execute any Composio tool via this mechanism represents a significant privilege, as it bypasses specific tool definitions and could allow for unintended or malicious actions if the LLM's instructions are subverted. Avoid exposing generic remote workbench execution capabilities to the LLM. If bulk operations are required, define them as specific, narrowly scoped tools with predefined parameters. Ensure that the `run_composio_tool()` function, if used, is strictly limited to a whitelist of safe and necessary operations, and that any arguments passed to it are validated and sanitized to prevent command injection or unauthorized access to other Composio tools.	LLM	SKILL.md:74

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/7a79ddaec96f7c4e.svg)](https://skillshield.io/report/7a79ddaec96f7c4e)