Security Audit

browser-extension-builder

github.com/sickn33/antigravity-awesome-skills

AI SkillCommit e36d6fd3b3f6

TRUSTED

Scanned about 5 hours ago

Critical

Immediate action required

High

Priority fixes suggested

Medium

Best practices review

Low

Acknowledged / Tracked

Trust Assessment

browser-extension-builder 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 Broad Content Script Permissions (`<all_urls>`) in Template.

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

Dynamic Code

1 finding

Excessive Permissions

1 finding

Security Findings1

Severity	Finding	Layer	Location
HIGH	Broad Content Script Permissions (`<all_urls>`) in Template The provided Manifest V3 template for browser extensions includes a content script configured with `"matches": ["<all_urls>"]`. This grants the extension the ability to inject code and access the Document Object Model (DOM) of every webpage the user visits. This is an excessive permission that significantly increases the attack surface and the potential for data exfiltration, as demonstrated by the 'Basic Content Script' example which shows how to extract data from the page. Although the skill's 'Anti-Patterns' section correctly advises against requesting all permissions, the template itself provides a default that enables such broad access, which could lead to developers inadvertently creating insecure extensions. Modify the Manifest V3 template to use more specific `matches` patterns (e.g., `["https://.example.com/"]`) or leverage optional permissions. If `<all_urls>` is truly necessary, the template should explicitly highlight the security implications and guide the user on how to implement it securely and with clear user consent, rather than providing it as a default.	LLM	SKILL.md:65

Scan History

Embed Code

[![SkillShield](https://skillshield.io/api/v1/badge/2c334d1ddd25773d.svg)](https://skillshield.io/report/2c334d1ddd25773d)