Security Audit

test-app-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

test-app-automation received a trust score of 83/100, placing it in the Mostly Trusted category. This skill has passed most security checks with only minor considerations noted.

SkillShield's automated analysis identified 2 findings: 0 critical, 1 high, 1 medium, and 0 low severity. Key findings include Broad tool execution via RUBE_REMOTE_WORKBENCH, Unpinned dependency on 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

78%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Broad tool execution via RUBE_REMOTE_WORKBENCH The skill documentation mentions `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This tool appears to allow the execution of arbitrary Composio tools, potentially granting the LLM very broad capabilities beyond the stated 'Test App Automation' scope. If the underlying Composio tools have access to sensitive systems or data, this could lead to unauthorized actions or data manipulation. Restrict the capabilities of `RUBE_REMOTE_WORKBENCH` to only allow specific, whitelisted `test_app` operations, or provide more granular tools for specific bulk operations rather than a generic `run_composio_tool()`. Ensure that the LLM's access to `RUBE_REMOTE_WORKBENCH` is strictly controlled and monitored.	LLM	SKILL.md:58
MEDIUM	Unpinned dependency on Rube MCP The skill's manifest specifies a dependency on `mcp: ["rube"]` without a version constraint. This means the skill could interact with any version of the Rube MCP. Future versions of Rube could introduce breaking changes, new vulnerabilities, or altered behavior that might not be compatible or secure with the current skill's assumptions, leading to unexpected outcomes or security risks. If possible, specify a version constraint for the Rube MCP dependency in the manifest (e.g., `mcp: ["rube@1.0.0"]` or `mcp: ["rube@^1.0.0"]`) to ensure compatibility and stability. If version pinning is not directly supported for MCPs in this ecosystem, document the expected Rube MCP version and monitor for changes.	LLM	Manifest (frontmatter JSON)

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/a241b0cf423296f3.svg)](https://skillshield.io/report/a241b0cf423296f3)