pagespeed-enhancer

Pass

Audited by Gen Agent Trust Hub on Jul 9, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides utility commands for image optimization using common tools and libraries.
  • Includes Python snippets using the Pillow library to resize and optimize images (PIL.Image).
  • Includes Bash commands for cwebp, sips, and sharp (Node.js) to convert images to modern formats like WebP.
  • These commands are intended for local execution by the user to optimize project assets.
  • [PROMPT_INJECTION]: The skill features an indirect prompt injection surface as it is designed to ingest and process external data in the form of PageSpeed reports or URLs.
  • Ingestion points: PHASE 1 and 2 involve parsing user-provided report text or site content.
  • Boundary markers: None explicitly defined in the instructions.
  • Capability inventory: The agent can generate code snippets, modify configuration files (TOML/JSON), and suggest shell commands.
  • Sanitization: The skill follows a rigid, step-by-step batch workflow which acts as a structural control against arbitrary instruction following from untrusted data.
  • [EXTERNAL_DOWNLOADS]: The skill references well-known external services for legitimate web development purposes.
  • Fetches fonts and CSS from Google Fonts (fonts.googleapis.com, fonts.gstatic.com).
  • Provides examples of fetching RSS data from api.rss2json.com for demonstration of build-time optimization.
  • References standard verification tools such as securityheaders.com and Google's Rich Results Test.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 9, 2026, 07:08 AM
Security Audit — agent-trust-hub — pagespeed-enhancer