effect-uai-streaming-structured-output

Pass

Audited by Gen Agent Trust Hub on May 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill describes a methodology for processing JSONL streams from LLMs. It includes a TypeScript implementation using the @effect-uai/core and effect libraries. The provided example uses schema-based validation (Schema.Struct) to decode and verify model output, which is an effective mitigation against malformed data or injection attempts within structured outputs. No malicious patterns, hidden commands, or unauthorized data access were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 4, 2026, 03:13 PM