pagespeed-insights

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to audit external web pages, which involves ingesting untrusted third-party content that could potentially contain malicious instructions.
  • Ingestion points: Web page code and performance metrics analyzed during the audit process (referenced in SKILL.md under 'Audit Workflow').
  • Boundary markers: Absent; the skill does not provide specific instructions to delimit or ignore embedded instructions within the audited data.
  • Capability inventory: None; the skill contains instructional markdown only and does not define any scripts or tools in its manifest.
  • Sanitization: Absent; there are no requirements for validating or sanitizing the content of the audited pages before processing.
  • [EXTERNAL_DOWNLOADS]: The skill references various official developer resources and the author's own domain for documentation and tool access.
  • Evidence: Links to official Google Developers documentation (developers.google.com), web performance guides (web.dev), and the author's personal domain (enderpuentes.com).
  • Context: These resources are used appropriately for educational purposes and tool discovery within the scope of web performance auditing.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 01:10 PM