Security Audit

close-automation

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

CAUTION

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

close-automation received a trust score of 73/100, 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 Excessive Permissions: Destructive Action Capability, Supply Chain Risk: Unpinned External MCP Dependency.

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 e36d6fd3). 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

Network Access

1 finding

Shell Execution

1 finding

Excessive Permissions

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Excessive Permissions: Destructive Action Capability The skill grants the AI agent the ability to perform destructive actions, specifically `CLOSE_DELETE_CALL`, which allows permanent deletion of call records. While a legitimate CRM function, this capability, if misused by the LLM (e.g., through a malicious prompt), could lead to irreversible data loss. The skill does not describe any built-in safeguards or confirmation steps for such high-impact operations. Implement explicit confirmation steps or human-in-the-loop approval for destructive actions like `CLOSE_DELETE_CALL`. Consider restricting access to such tools or providing a 'dry run' mode. Ensure the LLM is explicitly instructed on when and how to use such tools responsibly, and to seek user confirmation.	LLM	SKILL.md:109
HIGH	Supply Chain Risk: Unpinned External MCP Dependency The skill has a direct and unpinned dependency on an external Managed Control Plane (MCP) hosted at `https://rube.app/mcp`. All core functionality of this skill (e.g., `CLOSE_CREATE_LEAD`, `CLOSE_DELETE_CALL`) is provided by this external service. A compromise of `rube.app` or its MCP could lead to the execution of arbitrary malicious code or actions through the tools exposed to the AI agent, without any version pinning or integrity checks defined within the skill itself. Implement mechanisms to verify the integrity and authenticity of external MCPs. If possible, pin dependencies to specific versions or hashes. Regularly audit the security posture of third-party services. Consider sandboxing the execution environment for tools provided by external MCPs.	LLM	SKILL.md:20

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/36bb2959fef87183.svg)](https://skillshield.io/report/36bb2959fef87183)