AgentDB Vector Search
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill documents the use of
npx agentdb@latestfor database administration, including initialization, querying, and performance benchmarking. These commands are standard for the tool's operation. - [EXTERNAL_DOWNLOADS]: Instructions include fetching the
agentdbpackage via the npm registry. This is the intended distribution method for the toolset provided by the vendor. - [REMOTE_CODE_EXECUTION]: The skill provides configuration steps to add an MCP (Model Context Protocol) server. This allows an AI agent to interface with the local database instance through a controlled communication protocol.
- [DATA_EXFILTRATION]: While the skill involves processing document data and query strings for embeddings (e.g., via OpenAI), these operations are essential to the primary function of a vector search engine and are performed through standard API integrations.
Audit Metadata