Security Audit

github-automation

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

TRUSTED

Scanned about 2 months ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

github-automation received a trust score of 85/100, 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 Excessive GitHub API Permissions Granted.

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

85%

Behavioral Risk Signals

Network Access

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Excessive GitHub API Permissions Granted The 'github-automation' skill provides access to a very broad range of powerful and potentially destructive GitHub API operations, including creating/deleting repositories, merging pull requests, updating repository settings, managing branch protection, and adding collaborators. While the skill documentation advises 'explicit user confirmation for destructive operations', this relies on the LLM agent's adherence to instructions. A compromised LLM agent using this skill could bypass these instructions and perform unauthorized and irreversible actions on GitHub repositories, leading to data loss, security breaches, or unauthorized code changes. Implement more granular permission scopes for the GitHub integration, if possible, allowing users to enable only the specific actions required. For highly sensitive operations (e.g., repository deletion, branch protection changes, merging to protected branches), consider requiring a human-in-the-loop approval mechanism that is enforced at the tool execution level, rather than relying solely on LLM instructions.	LLM	SKILL.md:200

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/07ea5968376ac253.svg)](https://skillshield.io/report/07ea5968376ac253)