web-quality-audit

Pass

Audited by Gen Agent Trust Hub on Aug 11, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill's primary instruction file, SKILL.md, provides a comprehensive framework for auditing web pages based on industry standards like Google Lighthouse. It contains no instructions that attempt to bypass safety filters or override agent behavior.
  • [COMMAND_EXECUTION]: The skill includes a bash script, scripts/analyze.sh, which performs local static analysis on HTML files. The script is well-authored, using set -euo pipefail for robust error handling and proper quoting of variables to prevent command injection. It uses standard utilities like grep, find, and jq to identify common web quality issues such as missing doctypes, viewport tags, or image alt attributes. The script is read-only and does not perform any network operations or file system modifications.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 11, 2026, 09:44 PM
Security Audit — agent-trust-hub — web-quality-audit