AgentDB Memory Patterns

Pass

Audited by Gen Agent Trust Hub on Mar 1, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs users to utilize npx agentdb@latest for database initialization and plugin management. These are standard operations for installing and running the vendor's official CLI tools.
  • [COMMAND_EXECUTION]: Provides various CLI commands for database operations such as init, query, stats, and benchmark. These commands interact with local database files (e.g., .$agents.db) for legitimate storage management and performance testing.
  • [REMOTE_CODE_EXECUTION]: Documentation includes steps to add the AgentDB MCP server to Claude Code using npx. This is a standard integration method for the Model Context Protocol using the vendor's package.
  • [DATA_EXFILTRATION]: Features an export command to save database vectors to a local JSON file (.$backup.json). No evidence of unauthorized data transmission to external or untrusted domains was found; network references are limited to official vendor sites like agentdb.ruv.io and GitHub repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 1, 2026, 04:32 PM