AgentDB Memory Patterns

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructions and documentation rely on the agentdb package, which is fetched and executed via npx agentdb@latest from the NPM registry. It also utilizes the agentic-flow library for API integrations. These resources are official components provided by the skill's author (ruvnet).
  • [COMMAND_EXECUTION]: The skill documentation provides several shell commands for database initialization (agentdb init), plugin creation (agentdb create-plugin), and starting an MCP server (agentdb mcp). These commands are standard for managing the AgentDB lifecycle and integrating it with platforms like Claude Code.
  • [INDIRECT_PROMPT_INJECTION]: As a memory management system, the skill is designed to store and retrieve interaction data, including conversation history and user preferences. This creates a surface for indirect prompt injection where malicious instructions embedded in stored data could potentially influence the agent when the memory is retrieved. The skill uses JSON.stringify for data handling, but does not explicitly demonstrate input sanitization or boundary markers in its code snippets.
  • Ingestion points: Data enters the system via adapter.insertPattern, db.storeMemory, and db.storeFact calls in SKILL.md.
  • Boundary markers: None identified in the provided implementation snippets.
  • Capability inventory: The skill facilitates file writing (database files), vector search, and model training operations as shown in SKILL.md and CLI examples.
  • Sanitization: The snippets show structured data handling (JSON), but no specific filtering for prompt injection patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 12:40 AM