Security Audit

encodian-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

encodian-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 Skill enables broad tool execution 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

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Skill enables broad tool execution via `RUBE_REMOTE_WORKBENCH` The skill documentation describes the `RUBE_REMOTE_WORKBENCH` tool, which supports `run_composio_tool()`. This capability allows the agent to execute arbitrary Composio tools available through the Rube MCP. This grants the agent a very broad set of permissions, limited only by the connected Encodian account's access and the range of Composio tools. If the agent is compromised or misinterprets instructions, it could perform actions far beyond its intended scope, leading to unauthorized data manipulation, access, or other unintended operations within the Encodian environment. 1. Restrict `RUBE_REMOTE_WORKBENCH`: If possible, configure the Rube MCP or the Composio integration to limit the specific Composio tools that `RUBE_REMOTE_WORKBENCH` can execute, or restrict its use to a predefined set of safe operations. 2. Least Privilege: Ensure the Encodian connection used by Rube MCP has the absolute minimum necessary permissions. 3. Granular Tool Access: If `run_composio_tool()` is too broad, consider if more granular tools can be exposed directly instead of a generic 'workbench' for bulk operations. 4. Agent Sandboxing/Monitoring: Implement strict sandboxing and monitoring for agents using this skill to detect and prevent unauthorized actions.	LLM	SKILL.md:68

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/6e0d491ae7d4614f.svg)](https://skillshield.io/report/6e0d491ae7d4614f)