Security Audit

many-chat-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

many-chat-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 Excessive Permissions and Command Injection 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

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Excessive Permissions and Command Injection via RUBE_REMOTE_WORKBENCH The skill recommends using `RUBE_REMOTE_WORKBENCH` for 'Bulk ops'. The name 'workbench' strongly implies a broad and potentially unconstrained execution environment. Without explicit documentation or guarantees that `RUBE_REMOTE_WORKBENCH` and its associated `run_composio_tool()` function are strictly sandboxed and validate inputs, this tool could allow for arbitrary code execution, shell commands, or file system access. This represents an excessive permission that could be exploited for command injection, data exfiltration, or other malicious activities if an attacker can manipulate the arguments passed to it. Clarify the exact capabilities and security boundaries of `RUBE_REMOTE_WORKBENCH`. If it allows arbitrary code execution, restrict its use or ensure strong sandboxing is in place. If `run_composio_tool()` is meant to be the only entry point, ensure it strictly validates and sanitizes all inputs and only executes pre-approved, sandboxed operations. Consider if such a powerful tool is necessary for a ManyChat automation skill, or if more granular, less risky tools could achieve the same functionality.	LLM	SKILL.md:76

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/7610e7241b39e3b6.svg)](https://skillshield.io/report/7610e7241b39e3b6)