realtime-websocket-patterns

Pass

Audited by Gen Agent Trust Hub on Oct 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill provides patterns for real-time communication that process untrusted data from external clients, creating a potential surface for indirect prompt injection.
  • Ingestion points: The websocket_endpoint in SKILL.md uses await websocket.receive_json() to ingest messages directly from connected clients.
  • Boundary markers: The provided implementation does not include delimiters or specific instructions to help an agent distinguish between system instructions and data received via WebSockets.
  • Capability inventory: The skill includes code for WebSocket connection management, Redis-based pub/sub broadcasting, and SSE event streaming via fastapi and sse-starlette.
  • Sanitization: The code snippets demonstrate basic JSON parsing and broadcasting but do not implement sanitization or validation filters to prevent malicious payloads from influencing downstream agent logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 6, 2026, 04:21 PM