Security Audit

sendloop-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

sendloop-automation received a trust score of 84/100, 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 Potential for Arbitrary Code Execution via RUBE_REMOTE_WORKBENCH, Broad Tool Access and Connection Management Permissions.

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

78%

Behavioral Risk Signals

Network Access

1 finding

Shell Execution

2 findings

Dynamic Code

2 findings

Excessive Permissions

2 findings

Security Findings2

Severity	Finding	Layer	Location
HIGH	Potential for Arbitrary Code Execution via RUBE_REMOTE_WORKBENCH The skill instructs the use of `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. The term 'Workbench' and the function `run_composio_tool()` strongly suggest a flexible execution environment that could allow arbitrary code execution or shell commands if not properly sandboxed. If an attacker can inject malicious code or commands into the arguments of `run_composio_tool()` via prompt injection, it could lead to command injection, data exfiltration, or unauthorized system access within the agent's environment or the connected MCP. Ensure `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()` are strictly sandboxed and only allow pre-defined, safe operations. Implement robust input validation and restrict the types of operations that can be performed. If arbitrary code execution is intended, clearly document the security implications and necessary isolation measures, and restrict its use to highly trusted contexts.	LLM	SKILL.md:73
MEDIUM	Broad Tool Access and Connection Management Permissions The skill grants the agent access to powerful Rube MCP tools: `RUBE_MANAGE_CONNECTIONS` and `RUBE_MULTI_EXECUTE_TOOL`. `RUBE_MANAGE_CONNECTIONS` allows the agent to establish, modify, or delete connections to external services (like Sendloop), which could expose sensitive configuration or disrupt service. `RUBE_MULTI_EXECUTE_TOOL` enables the execution of any tool discovered via `RUBE_SEARCH_TOOLS`, providing broad control over Sendloop operations. This combination of permissions, if misused (e.g., through prompt injection), could lead to unauthorized actions, data manipulation, or service disruption on connected third-party platforms. Implement strict access controls and input validation for `RUBE_MANAGE_CONNECTIONS` and `RUBE_MULTI_EXECUTE_TOOL`. Ensure that the agent's access to these tools is limited to the minimum necessary scope for its intended function. Consider fine-grained permissions for specific Sendloop operations rather than blanket execution capabilities.	LLM	SKILL.md:71

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/a87ab55c160a8034.svg)](https://skillshield.io/report/a87ab55c160a8034)