Security Audit

upgrading-expo

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

upgrading-expo 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 Skill instructs execution of shell commands, Unpinned dependency versions for critical tools.

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

Dynamic Code

1 finding

Security Findings2

Severity	Finding	Layer	Location
HIGH	Skill instructs execution of shell commands The skill provides multiple shell command blocks (`npm install`, `npx expo install`, `npx expo-doctor`). If an AI agent is configured to execute shell commands directly from skill instructions, this constitutes a command injection vulnerability. The `npm install -g expo-cli@latest` command is particularly concerning as it performs a global installation, potentially affecting the entire system rather than just the project directory. While the commands themselves are for legitimate development tools, the mechanism allows for arbitrary code execution if the skill content were altered or if the agent's execution environment is not properly sandboxed. AI agent execution environments should strictly sandbox shell command execution, require explicit user confirmation for any commands, and ideally, disallow global installations. Skills should minimize direct shell command instructions where possible, or provide them in a way that clearly distinguishes between instructions for a human user and commands for an automated agent.	LLM	SKILL.md:39
HIGH	Unpinned dependency versions for critical tools The skill instructs users to install `expo-cli` and `expo` using the `@latest` tag. This means the skill will always fetch the newest version available, which could introduce breaking changes or, more critically, a compromised version if the `latest` tag in the npm registry is hijacked. Pinning to specific major/minor versions (e.g., `expo-cli@^X.Y.Z` or `expo@X.Y.Z`) is recommended for stability and security. Replace `@latest` with a specific version or a version range (e.g., `expo-cli@^X.Y.Z`, `expo@X.Y.Z`) to ensure deterministic and secure dependency resolution.	LLM	SKILL.md:40

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/8e7cf7fec485b125.svg)](https://skillshield.io/report/8e7cf7fec485b125)