zero-build-frontend

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides detailed instructions for securing the frontend supply chain by vendoring dependencies, using exact versions, and verifying hashes (e.g., using sha256sum in references/dependency-assets.md).
  • [SAFE]: It specifically recommends CSP-compliant versions of libraries, such as the Alpine.js CSP build, to prevent the use of unsafe-eval and improve security posture.
  • [INDIRECT_PROMPT_INJECTION]: The skill documents procedures for handling untrusted data from external sources like Google Sheets (CSV) or JSON APIs in SKILL.md and references/google-sheets.md. It includes an 'Untrusted content boundary' contract that mandates schema validation and visible delimiting of external data to mitigate injection risks. This is documented as a security best practice for the intended workflow.
  • [SAFE]: Network operations described in the templates target well-known services (Bitly for shortlink creation, Google Sheets for data storage, Carto for map tiles). The browser extension example in references/browser-extensions.md follows standard Manifest V3 practices for permission management and secure storage of user-provided API tokens.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:01 AM
Security Audit — agent-trust-hub — zero-build-frontend