skills/sebas-aikon-intelligence/antigravity-awesome-skills/browser-extension-builder/Gen Agent Trust Hub
browser-extension-builder
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides templates for content scripts that ingest data from arbitrary web pages using
document.querySelector. This creates a standard attack surface for indirect prompt injection, as the agent processes untrusted external data. - Ingestion points:
SKILL.md(Content Scripts section) defines code that reads DOM content. - Boundary markers: Absent in the provided code snippets.
- Capability inventory: File reads/writes (via
chrome.storage), DOM manipulation, and message passing between extension components. - Sanitization: The provided examples do not demonstrate sanitization or validation of the text content extracted from web pages.
- [SAFE]: The skill includes an 'Anti-Patterns' section that correctly identifies and warns against high-risk behaviors such as requesting excessive permissions (
<all_urls>) and heavy background processing. The code examples use official, documented browser APIs (chrome.storage,chrome.runtime) and follow Manifest V3 standards.
Audit Metadata