browser-required

Pass

Audited by Gen Agent Trust Hub on Oct 7, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill references the installation of the Lighthouse package via npm and provides links to well-known performance auditing services such as WebPageTest.org, PageSpeed Insights, and Google's web.dev documentation. These are trusted industry resources.
  • [COMMAND_EXECUTION]: Documentation includes example shell commands for running Lighthouse and JavaScript snippets for using Puppeteer. These are provided as educational templates for standard performance testing workflows and do not contain malicious intent.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to audit external URLs which inherently involves processing untrusted data. However, the skill provides high-level guidance rather than implementing automated ingestion, and the risk is considered minimal for this educational use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 7, 2026, 10:57 PM