websocket-realtime-builder

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill includes instructions to install socket.io and socket.io-client through standard package management. These are well-known and widely used libraries for WebSocket communication.
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and distribution of user-provided text messages through a WebSocket server and client interface.
  • Ingestion points: User-provided strings enter the system via the send-message event handler in the server-side code within SKILL.md.
  • Boundary markers: The templates do not include specific delimiters or instructional barriers to prevent an agent from potentially interpreting user-generated content as commands.
  • Capability inventory: The system has capabilities to store content in a database (db.message.create) and broadcast it to other users through network emissions (emit).
  • Sanitization: There is no content validation or escaping logic present in the provided templates to sanitize user-generated strings before they are processed or displayed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 06:14 PM
Security Audit — agent-trust-hub — websocket-realtime-builder