reasoningbank-agentdb
Pass
Audited by Gen Agent Trust Hub on Jun 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides instructions for building self-learning agents using documented libraries. No malicious patterns, prompt injections, or unauthorized data access were detected.
- [EXTERNAL_DOWNLOADS]: The skill utilizes
npx agentdb@latestto initialize and manage the database environment. This command fetches the legitimate CLI tool from the public NPM registry, which is a standard distribution method for Node.js developer tools. - [COMMAND_EXECUTION]: Several CLI commands are provided for database management, including
init,migrate,stats, andmcp. These commands operate on local files (e.g.,./.agentdb/reasoningbank.db) and are used to configure the agent's memory backend. - [REMOTE_CODE_EXECUTION]: The integration with Claude via
claude mcp addallows the agent to use the AgentDB tool. This is a standard extension mechanism for MCP-compatible agents and does not involve untrusted remote execution.
Audit Metadata