Security Audit

open-sea-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 99e2a2951545

TRUSTED

Scanned 6 days ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

open-sea-automation received a trust score of 95/100, placing it in the Trusted category. This skill has passed all critical security checks and demonstrates strong security practices.

SkillShield's automated analysis identified 1 finding: 0 critical, 0 high, 1 medium, and 0 low severity. Key findings include Skill exposes broad tool execution capabilities via Rube MCP.

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

93%

Behavioral Risk Signals

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
MEDIUM	Skill exposes broad tool execution capabilities via Rube MCP The skill documentation describes the use of `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`, which allows for 'Bulk ops' and the execution of arbitrary Composio tools. While this is a core feature of the Composio ecosystem, granting an AI agent access to such a broad tool can lead to unintended actions or misuse if the agent is compromised or misinterprets instructions. The scope of actions possible through `run_composio_tool()` is not explicitly limited within this skill's definition, potentially allowing operations beyond Open Sea if other Composio tools are accessible via Rube MCP. Consider if the `RUBE_REMOTE_WORKBENCH` tool is strictly necessary for the intended scope of this skill. If not, remove its documentation and restrict its availability to the agent. If necessary, implement stricter guardrails or explicit limitations on the types of `composio_tool()` calls allowed, or ensure the LLM's prompt engineering includes strong safety measures against arbitrary tool execution.	LLM	SKILL.md:65

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/003865d268ae5a5b.svg)](https://skillshield.io/report/003865d268ae5a5b)