Security Audit

Sounder25/Google-Antigravity-Skills-Library:12_dependency_tree_mapping

github.com/Sounder25/Google-Antigravity-Skills-Library

AI SkillCommit 09376edc64e9

TRUSTED

Scanned about 1 month ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

Sounder25/Google-Antigravity-Skills-Library:12_dependency_tree_mapping 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 Potential Command Injection via User Inputs.

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 28, 2026 (commit 09376edc). 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

Filesystem Write

1 finding

Shell Execution

1 finding

Dynamic Code

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Potential Command Injection via User Inputs The skill's implementation explicitly states it executes external command-line tools such as `npm`, `dotnet`, and `pipdeptree` to extract dependency graphs. User-provided inputs, specifically `--workspace-path` and the `<library>` name from trigger phrases like `check impact of <library>`, are likely to be interpolated into these shell commands. Without robust input sanitization and proper escaping, a malicious user could inject arbitrary shell commands by crafting these inputs, leading to remote code execution. The implementation is described as a PowerShell script (`map_dependencies.ps1`), which further emphasizes the need for careful handling of external process execution. Implement strict input validation and sanitization for all user-provided parameters (`--workspace-path`, `<library>`). When executing external commands, use safe methods that pass arguments as a list rather than constructing a single shell string (e.g., `Start-Process -FilePath ... -ArgumentList ...` in PowerShell) to prevent shell metacharacter interpretation. Ensure all paths and library names are properly quoted and escaped if direct string interpolation is unavoidable.	LLM	SKILL.md:39

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/45878cb58801d2f6.svg)](https://skillshield.io/report/45878cb58801d2f6)