mobile-real-time

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill facilitates the ingestion of data from untrusted external sources (WebSockets, Supabase Realtime, and Server-Sent Events), creating a surface for indirect prompt injection.
  • Ingestion points: Data enters the application through event listeners in useWebSocket, useRealtimeTable, and useSSE hooks within SKILL.md.
  • Boundary markers: The instructions do not define delimiters or provide guidance to the agent on how to distinguish between data and instructions within these streams.
  • Capability inventory: While primarily focused on UI state management, the agent using this skill might possess other capabilities (e.g., file writing, command execution) that could be targeted by instructions embedded in the real-time data.
  • Sanitization: The provided code snippets perform JSON.parse on incoming data but lack input validation or sanitization before the data is used to update the application state.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 12:29 PM
Security Audit — agent-trust-hub — mobile-real-time