fishjam-js-server-sdk
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: Installs the
@fishjam-cloud/js-server-sdklibrary and the optional@google/genaidependency. These are official packages from the vendor and a well-known service provider respectively. - [SAFE]: Promotes secure credential handling by utilizing environment variables for management tokens and providing explicit warnings against exposing them in client-facing code.
- [SAFE]: Implements secure webhook handling patterns through path-based secrets, ensuring that only authorized notifications from the Fishjam platform are processed.
- [SAFE]: Provides a structured surface for AI agent development with well-defined data ingestion and capability boundaries.
- [SAFE]: (Indirect Prompt Injection Surface Analysis) The skill enables processing of external media data. Ingestion points: Receives audio via
agent.on('trackData')and video frames viaagent.captureImage()inagent.md. Boundary markers: Relies on the integrated AI model's internal safety filters as no explicit prompt delimiters are provided for the audio/image streams. Capability inventory: Includes capabilities to manipulate room state and send media data via theFishjamClientandFishjamAgentclasses. Sanitization: Standard for media SDKs, it passes raw binary data to processors without content-level sanitization.
Audit Metadata