helix-memory-system

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill provides architectural patterns and code examples for implementing long-term memory using the author's official TypeScript and Rust libraries.
  • [DATA_EXPOSURE]: Includes mandatory isolation rules requiring tenant_id and userId filtering on all read and write operations to prevent cross-tenant or cross-user data exposure.
  • [EXTERNAL_DOWNLOADS]: References official vendor packages (@helix-db/helix-db) and well-known services (OpenAI) for embeddings, which are standard for the described use case.
  • [PROMPT_INJECTION]: While the skill processes untrusted user data to create memories (Indirect Prompt Injection surface), it recommends structural extraction and application-layer adjudication to mitigate malicious instruction processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 06:52 AM
Security Audit — agent-trust-hub — helix-memory-system