Security Audit

microsoft-tenant-automation

github.com/ComposioHQ/awesome-claude-skills

AI SkillCommit 27904475d127

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

microsoft-tenant-automation received a trust score of 74/100, placing it in the Caution category. This skill has some security considerations that users should review before deployment.

SkillShield's automated analysis identified 2 findings: 0 critical, 2 high, 0 medium, and 0 low severity. Key findings include Unpinned MCP dependency, Exposure of highly privileged tool primitive.

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

70%

Behavioral Risk Signals

Shell Execution

1 finding

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Unpinned MCP dependency The skill manifest specifies a dependency on the 'rube' MCP without a version constraint. This means the skill will always use the latest version, which could lead to unexpected behavior, breaking changes, or the introduction of malicious code if the MCP provider is compromised or changes its service. Relying on unpinned dependencies introduces a supply chain risk. Pin the MCP dependency to a specific version or version range in the manifest to ensure stability and security. Regularly review and update pinned versions.	LLM	SKILL.md
HIGH	Exposure of highly privileged tool primitive The skill documentation explicitly mentions and provides guidance for using `RUBE_REMOTE_WORKBENCH` with `run_composio_tool()`. This primitive allows the execution of arbitrary Composio tools, granting a very broad scope of capabilities. If an attacker can manipulate the arguments passed to `run_composio_tool()` (e.g., through prompt injection to the agent), they could potentially execute any action available via the Composio ecosystem, leading to unauthorized data access, modification, or deletion within the connected Microsoft Tenant. Implement strict input validation and sanitization for arguments passed to `RUBE_REMOTE_WORKBENCH` and `run_composio_tool()`. Consider restricting the set of tools that can be executed via `run_composio_tool()` or requiring explicit user confirmation for sensitive operations. Provide clear warnings about the power of this primitive to the agent and end-user.	LLM	SKILL.md:80

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/765eb20823f1ee66.svg)](https://skillshield.io/report/765eb20823f1ee66)