Security Audit

appdrag-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

appdrag-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 via RUBE_REMOTE_WORKBENCH.

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

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad Tool Execution via RUBE_REMOTE_WORKBENCH The skill exposes the `RUBE_REMOTE_WORKBENCH` tool, which is described as enabling 'Bulk ops' and the execution of `run_composio_tool()`. This implies a highly privileged and flexible execution environment that can potentially run arbitrary Composio tools or complex sequences of operations on the Appdrag platform. An AI agent, if compromised by a prompt injection, could be instructed to leverage this tool for unauthorized actions, data manipulation, or data exfiltration on Appdrag, bypassing more granular controls that might exist for individual tools. 1. Least Privilege: If possible, restrict the capabilities of `RUBE_REMOTE_WORKBENCH` to a predefined, limited set of safe operations. 2. Granular Permissions: Implement more granular permissions for `run_composio_tool()` calls, requiring explicit approval or whitelisting for sensitive operations. 3. Input Validation: Ensure robust input validation and sanitization for any arguments passed to `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` to prevent malicious payloads. 4. User Confirmation: For critical operations, require explicit user confirmation before executing actions via `RUBE_REMOTE_WORKBENCH`.	LLM	SKILL.md:82

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/7f5d289a82d15660.svg)](https://skillshield.io/report/7f5d289a82d15660)