Security Audit

sendloop-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

sendloop-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, 0 high, 1 medium, and 0 low severity. Key findings include Dynamic tool discovery and execution allows broad 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

93%

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
MEDIUM	Dynamic tool discovery and execution allows broad access The skill instructs the LLM to dynamically discover tools using `RUBE_SEARCH_TOOLS` and then execute them via `RUBE_MULTI_EXECUTE_TOOL` or `RUBE_REMOTE_WORKBENCH`. This design pattern means the LLM could potentially discover and execute any tool exposed by the Rube MCP system, not just those strictly related to Sendloop. If the Rube MCP system exposes tools with broad permissions (e.g., filesystem access, arbitrary network requests, or access to other sensitive systems), and the LLM is prompted to use them, this skill's instructions could lead to excessive permissions. The `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` is particularly powerful as it suggests a generic tool execution capability. Restrict the scope of tools discoverable by `RUBE_SEARCH_TOOLS` to only Sendloop-specific operations. Implement explicit whitelisting or sandboxing for tools executed via `RUBE_MULTI_EXECUTE_TOOL` and `RUBE_REMOTE_WORKBENCH` to ensure they cannot perform actions outside the intended scope of Sendloop automation. If `RUBE_REMOTE_WORKBENCH` is intended for generic tool execution, ensure robust access controls and sandboxing are in place at the Rube MCP level, and consider if this skill truly requires such a broad capability.	LLM	SKILL.md:24

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/d03e5e46ef6cde23.svg)](https://skillshield.io/report/d03e5e46ef6cde23)