bx-ai-memory

Pass

Audited by Gen Agent Trust Hub on Apr 15, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a reference guide for the aiMemory() function, providing examples for various persistence strategies including in-memory, file-based, and database-backed storage.
  • [SAFE]: Includes explicit security warnings, specifically advising against storing API keys or secrets within the memory system.
  • [SAFE]: Implements multi-tenant isolation as a core feature, instructing users on how to separate data using userId and conversationId to prevent cross-user data leakage.
  • [SAFE]: The documentation for vector memory and external providers (e.g., ChromaDB, Pinecone) uses standard configuration patterns and does not involve downloading untrusted scripts or executing remote code.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 15, 2026, 02:43 PM