Security Audit

benchmark-email-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

benchmark-email-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 Excessive Permissions via RUBE_REMOTE_WORKBENCH and run_composio_tool().

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	Excessive Permissions via RUBE_REMOTE_WORKBENCH and run_composio_tool() The skill instructs the agent to use `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()` for 'Bulk ops'. This tool, as described, appears to offer a broad execution capability within the Composio ecosystem. If `run_composio_tool()` can execute arbitrary Composio tools or commands without sufficient sandboxing or scope limitation, it could allow an agent to perform actions beyond the intended 'Benchmark Email automation' scope. This could lead to unintended data access, modification, or system-level operations on connected services or the Rube MCP environment. The skill's documentation does not specify any restrictions on what `run_composio_tool()` can execute, presenting a significant risk of over-privilege or potential command injection within the Rube environment. Clarify the exact scope and limitations of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that `run_composio_tool()` is strictly limited to operations relevant to Benchmark Email or that its execution context is heavily sandboxed. If it allows arbitrary tool execution, consider if this skill truly requires such a broad capability, or if more specific, scoped tools should be used instead.	LLM	SKILL.md:100

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/c9e10f83516be861.svg)](https://skillshield.io/report/c9e10f83516be861)