Security Audit

reply-io-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

reply-io-automation received a trust score of 88/100, 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 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 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

85%

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
HIGH	Potential Excessive Permissions via RUBE_REMOTE_WORKBENCH The skill's documentation mentions `RUBE_REMOTE_WORKBENCH` with the capability to `run_composio_tool()`. This generic phrasing suggests the ability to execute any tool provided by Composio, not just those specifically related to Reply IO. If the underlying `rube` MCP or Composio platform offers tools with broader system access (e.g., filesystem access, arbitrary command execution, network interactions beyond Reply IO), this could allow the LLM to perform actions outside the intended scope of 'Reply IO Automation'. This represents an excessive permission for a skill explicitly designed for Reply IO tasks, potentially leading to unauthorized operations or command injection if a malicious prompt induces the LLM to invoke a powerful, non-Reply IO tool. Clarify the precise scope and limitations of `run_composio_tool()` when used with `RUBE_REMOTE_WORKBENCH`. If it can execute arbitrary Composio tools, restrict its functionality within this skill to only Reply IO-specific tools. Alternatively, if broader tool execution is intended, update the skill's description and manifest to accurately reflect this wider scope and document the security implications. Implement strict validation on the tool identifier passed to `run_composio_tool()` to ensure only authorized tools are invoked.	LLM	SKILL.md:68

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/965ec845b8187061.svg)](https://skillshield.io/report/965ec845b8187061)