Skills
skills/aj-geddes/useful-ai-prompts/progressive-web-app/Gen Agent Trust Hub

progressive-web-app

Pass

Audited by Gen Agent Trust Hub on Mar 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface detected in the provided PWA templates.\n
  • Ingestion points: references/service-worker-implementation.md (intercepting network fetch events) and references/push-notifications.md (handling data from push notification payloads).\n
  • Boundary markers: No delimiters or explicit instructions to treat incoming network data as untrusted are included in the template code.\n
  • Capability inventory: The templates use fetch for network operations, IndexedDB for local storage, and CacheStorage for managing offline resources.\n
  • Sanitization: No data sanitization or validation logic is present in the snippets for processing data received from external API endpoints or push services.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 5, 2026, 01:51 AM