Security Audit

endorsal-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

endorsal-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 Potential Command Injection / Excessive Permissions 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	Potential Command Injection / Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill instructs the LLM to use `RUBE_REMOTE_WORKBENCH` for 'Bulk ops' with `run_composio_tool()`. The term 'workbench' and the function `run_composio_tool()` are highly suggestive of capabilities for executing arbitrary code or complex operations. If the arguments passed to `run_composio_tool()` are not strictly controlled, validated, and sandboxed by the Rube MCP, an attacker could craft inputs to achieve command injection, execute arbitrary code, or perform actions with excessive permissions. This could lead to data exfiltration, unauthorized access, or system compromise. The skill itself does not define the exact capabilities or security measures of `RUBE_REMOTE_WORKBENCH`. Clarify the exact capabilities and security model of `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Ensure that any code execution is strictly sandboxed, arguments are thoroughly validated, and the LLM cannot inject arbitrary commands or scripts. If arbitrary code execution is an intended feature, clearly document the security implications and necessary safeguards for users. Consider if this broad functionality is truly necessary for the skill's stated purpose, or if more specific, limited tools could be used instead.	LLM	SKILL.md:63

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/972ac1e685e393d9.svg)](https://skillshield.io/report/972ac1e685e393d9)